阅读说明：本技术 临床决策支持 (Clinical decision support ) 是由 R·温贝格尔-弗里德尔 V·L·d·C·比托里诺德阿尔梅达 P·J·达席尔瓦罗德里格斯 A·I 于 2018-10-19 设计创作，主要内容包括：公开了一种临床决策支持系统(100)。临床决策支持系统(100)包括处理器(102),处理器(102)被配置为：建立用于根据多个特征定义对象的对象简档；识别与所述对象相关的一组临床试验,其中,该组相关临床试验中的每个临床试验对应于至少一个治疗,所述至少一个治疗具有由对象简档的多个特征中的特征所满足的纳入准则；对与相关临床试验相对应的治疗进行排名；并且输出针对对象的治疗的排名。还公开了一种方法和计算机程序产品。(A clinical decision support system (100) is disclosed. The clinical decision support system (100) comprises a processor (102), the processor (102) being configured to: establishing an object profile for defining an object according to a plurality of features; identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment having inclusion criteria that are satisfied by a feature of a plurality of features of a profile of the subject; ranking treatments corresponding to relevant clinical trials; and outputting a ranking of treatments for the subject. A method and computer program product are also disclosed.)

1. A clinical decision support system (100) comprising:

a processor (102) configured to:

establishing a subject profile for defining a subject with cancer based on a plurality of features;

identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile;

ranking the treatments corresponding to the relevant clinical trials; and is

Outputting the ranking of the treatment for the subject;

wherein the treatment comprises immunotherapy against cancer.

2. The clinical decision support system (100) according to claim 1, wherein to rank the treatments, the processor (102) is configured to:

the identified set of clinical trials is ranked based on the clinical benefit achieved by each clinical trial.

3. The clinical decision support system (100) according to claim 2, wherein the processor (102) is configured to:

ranking the identified set of clinical trials according to at least one of: similarity of a feature of the subject to a corresponding feature of a participant of the clinical trial; and the level of information available about the clinical trial.

4. The clinical decision support system (100) according to claim 2 or claim 3, wherein the clinical benefit achieved by a clinical trial is defined by at least one of: a measure of progression-free survival of a participant in the clinical trial; a measure of overall survival of participants in the clinical trial; and a measure of the participant's response rate in the clinical trial.

5. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

ranking the treatments based on weighted scores.

6. The clinical decision support system (100) according to claim 5, wherein the weighted score is based on at least one of:

a satisfaction score that indicates a degree of satisfaction of the inclusion criteria by the plurality of features of the subject profile;

a result score indicating the extent to which each trial achieved clinical benefit; and

a complementary effect score indicating a measure of the expected side effects caused by each trial.

7. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

the subject profile is established by obtaining clinical information related to the subject from a clinical database (208).

8. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

the set of clinical trials is identified by searching a clinical trial database (206) that includes at least the clinical trials for which result data has been provided.

9. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

grouping the ranked treatments according to at least one of: biological similarities between the treatments; and similarities between features of the subject profile and features of profiles of participants in the set of clinical trials.

10. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

presenting the output ranked treatments to the user along with at least one of: the expected benefit of each presented treatment; and the potential risks associated with each presented treatment.

11. The clinical decision support system (100) according to any one of the preceding claims, wherein a clinical trial is related to the subject if a threshold number of inclusion criteria is met by features of the subject profile.

12. A method (300) for ranking a plurality of treatments for a subject having cancer, the method comprising:

establishing (302) an object profile defining an object according to a plurality of features;

identifying (304) a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile;

ranking (306) the treatments corresponding to the relevant clinical trials; and is

Outputting (308) the ranking of the treatment for the subject;

wherein the treatment comprises immunotherapy against cancer.

13. The method (300, 400) of claim 12, further comprising:

applying (402) a weighted score to each therapy;

wherein the ranking (306) is based on the applied weighted score.

14. The method (300, 400) of claim 13, wherein the weighted score is based on at least one of:

a satisfaction score that indicates a degree of satisfaction of the inclusion criteria by the plurality of features of the subject profile;

a result score indicating the extent to which each trial achieved clinical benefit; and

a complementary effect score indicating a measure of the expected side effects caused by each trial.

15. A computer program product comprising a non-transitory computer-readable medium (602) having computer-readable code embodied therein, the computer-readable code being configured such that, on execution by a suitable computer or processor (604), the computer or processor is caused to perform the method of any of claims 12 to 14.

Technical Field

The present invention relates to clinical decision support, and more particularly, to systems and methods for ranking treatments related to a subject.

Background

Clinical guidelines or clinical pathways are often used to aid a clinician in decision making when the clinician is required to select a treatment to be provided to a subject. The selected therapy may be provided to the subject for a period of time during which the subject's response to the therapy may be monitored. With respect to some diseases, such as cancer, treatment may result in an increase in the resistance of the disease to treatment, and may result in the progression (i.e., worsening) of the disease.

For some diseases, the first and second therapies (referred to as first-line and second-line therapies) may be unsuccessful, and as a result, subsequent therapies (e.g., third-line therapies) may have little or no treatment purpose, but may be intended to extend life expectancy at a reasonable quality, or to reduce symptoms affecting life quality without extending life expectancy. In this situation, clinical guidelines and clinical pathways provide little help, as there are often no recognized standard care pathways. Thus, the clinician may select a treatment for the subject based on his or her own knowledge or based on scientific literature.

Clinical trials were performed to investigate the effect that various new or adapted treatments have on different people, with the ultimate goal of improving the standard of care. A clinical trial may include multiple arms, each arm including a group of participants receiving a particular treatment. Some arms of the clinical trial may involve combinations of treatments being provided to a single participant group. With so many clinical trials taking place, and the large number of possible treatment combinations, it may be difficult for a clinician to remain aware of the various treatment options available and appropriate for their subject.

These problems are particularly prevalent in the field of immunotherapy for use in cancer treatment. The number of clinical trials in this area has increased rapidly as a number of new immunotherapeutic options have been developed.

Therefore, there is a need for a system that enables clinicians to make more informed decisions about which treatment or treatments may be appropriate for their subjects.

Disclosure of Invention

According to an aspect of the invention, a clinical decision support system comprising a processor is provided. The processor is configured to: establishing an object profile for defining an object according to a plurality of features; identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile; ranking treatments corresponding to relevant clinical trials; and outputting a treatment ranking for the subject. Such a system may provide a user (e.g., a clinician or subject) with a list of relevant treatments for the subject based on clinical trials that may be running or have successfully completed and for which the subject may have been qualified. By evaluating the treatment corresponding to such a clinical trial, the clinician may gain a greater understanding or appreciation of possible treatment options that can be appropriate for the subject.

In one embodiment, the subject is suffering from cancer. In some embodiments, the treatment comprises immunotherapy against cancer.

In some embodiments, to rank the treatments, the processor may be configured to rank the identified set of clinical trials based on the clinical benefit achieved by each clinical trial.

The processor may be configured to rank the identified set of clinical trials according to at least one of: similarity of a characteristic of the subject to a corresponding characteristic of a participant of the clinical trial; and the level of information available about the clinical trial.

The clinical benefit achieved by a clinical trial may be defined by at least one of: a measure of progression-free survival of the participants in the clinical trial; a measure of overall survival of the participants in the clinical trial; and a measure of the participant's response rate in a clinical trial.

In some embodiments, the processor may be configured to rank the treatments based on the weighted scores. The weighted score may be based on at least one of: a satisfaction score indicating a degree of satisfaction of the inclusion criteria by a plurality of features of the subject profile; a result score indicating the extent to which each trial achieved clinical benefit; and a complementary effect score indicating a measure of the expected side effects caused by each test.

In some embodiments, the processor may be configured to establish the subject profile by obtaining clinical information related to the subject from a clinical database.

The processor may be configured to identify a set of clinical trials by searching a clinical trial database that includes at least the clinical trials for which result data has been provided. For example, the clinical trial database may include trials that have ended.

In some embodiments, the processor may be configured to group the ranked treatments according to at least one of: biological similarities between treatments; and similarities between features of the subject's profile and features of the profiles of the participants in the set of clinical trials.

The processor may be configured to present the output ranked therapy to the user along with at least one of: the expected benefit of each presented treatment; and the potential risks associated with each presented treatment.

In some embodiments, a clinical trial may be considered relevant to a subject if a threshold number of inclusion criteria is met by features of the subject profile.

According to another aspect of the invention, a method for ranking a plurality of treatments for a subject is provided. The method comprises the following steps: establishing an object profile for defining an object in accordance with a plurality of features; identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of a plurality of features of a profile of the subject; ranking treatments corresponding to relevant clinical trials; and outputting a ranking of treatments for the subject.

In some embodiments, the method may further comprise applying a weighted score to each treatment. The ranking may be based on the applied weighted scores. In some embodiments, the weighted score may be based on at least one of: a satisfaction score indicating a degree of satisfaction of the inclusion criteria by a plurality of features of the subject profile; a result score indicating the extent to which each trial achieved clinical benefit; and a complementary effect score indicating a measure of the expected side effects caused by each test.

According to another aspect of the invention, there is provided a computer program product comprising a non-transitory computer-readable medium having computer-readable code embodied therein, the computer-readable code being configured such that, on execution by a suitable computer or processor, the computer or processor is caused to perform any of the methods disclosed herein.

According to another aspect of the invention, a clinical decision support system (100) is provided, comprising: a processor (102) configured to: establishing an object profile for defining an object according to a plurality of features; identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has associated inclusion criteria, and wherein each clinical trial has inclusion criteria that matches a feature in a plurality of features of the subject profile; ranking treatments corresponding to relevant clinical trials; and outputting a ranking of treatments for the subject.

According to a further aspect of the present invention there is provided a device for providing clinical decision support, the device comprising: a profiling unit for defining a profile of the object based on a plurality of features; an identification unit for identifying a set of clinical trials related to the subject, wherein each clinical trial of the set of related clinical trials corresponds to at least one treatment and has an associated inclusion criterion, and wherein each clinical trial has an inclusion criterion that matches a feature of a plurality of features of a profile of the subject; a ranking unit for ranking treatments corresponding to relevant clinical trials; and a display for displaying the ranking of treatments.

These and other aspects of the invention are apparent from and will be elucidated with reference to the embodiments described hereinafter.

Drawings

For a better understanding of the present invention, and to show more clearly how it may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

fig. 1 is a simplified schematic diagram of an example of a system according to an embodiment;

fig. 2 is a simplified schematic diagram of a further example of a system according to an embodiment;

fig. 3 is a flow diagram of an example of a method for ranking treatments according to an embodiment;

fig. 4 is a flow diagram of a further example of a method for ranking treatments according to an embodiment;

fig. 5 is a flow diagram of a further example of a method for ranking treatments according to an embodiment; and is

Fig. 6 is a simplified schematic diagram of a computer-readable medium and a processor.

Detailed Description

The inventors have found that information about clinical trials that have previously occurred can be used to obtain valuable information about the suitability of a treatment for a subject (e.g. a patient). For example, data relating to an already concluded clinical trial (for which a particular subject would have been eligible) may be examined and then used to decide whether a treatment (e.g., a treatment studied as part of a previous clinical trial) is appropriate for the particular subject and may provide a clinical benefit to the particular subject.

As shown in fig. 1, aspects of the present invention may be implemented as an apparatus or system. Fig. 1 shows an example of an apparatus or system, such as a clinical support system 100, that includes a processor 102. System 100 may include a computing device, such as a desktop computer, laptop or tablet computer, smart phone, server, network of computing devices, or any other apparatus or system with suitable processing functionality.

In some embodiments, the processor 102 is configured to establish an object profile for defining the object based on the plurality of characteristics. The subject may, for example, be a patient under the care of one or more clinicians or medical professionals. The subject profile may include any data related to the subject, such as personal data related to the subject (e.g., name, age, and gender), medical data related to the subject (e.g., current and previous medical conditions, previous and current treatments and therapies, data collected from medical records, such as Electronic Medical Records (EMRs), laboratory data, and pathology reports), or any combination of such data. The characteristics of the subject profile may include one or more items of data included in the profile. For example, the feature may be that the subject is a female; another characteristic may be that the subject is 54 years of age; another feature may be that the subject has been previously treated for a particular type of cancer, and so on.

In some embodiments, processor 102 may automatically establish an object profile, for example, by assembling, interpreting, and/or combining data from different records that relate to a single object identification number. In some examples, the object or object data may be manually entered, for example, by a medical professional or clinician. In some embodiments, the processor 102 may be configured to establish a subject profile by obtaining clinical information related to the subject from a clinical database. Such a clinical database may form part of the system 100 or may be remote from the system, accessible by the processor 102. For example, a clinical database may include clinical data relating to a plurality of subjects at a particular medical facility or medical institution or organization.

In some embodiments, the processor 102 is further configured to identify a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile. The inclusion criteria for a clinical trial is that the subject must meet a set of requirements in order to participate in the trial. For example, inclusion criteria for a particular clinical trial may include that the participant is male, between the ages of 50 and 55, and has a particular medical condition. A subject can be eligible for participation in a clinical trial if it meets the criteria. Features included in the subject profile may be used to determine whether the subject is eligible to participate. A particular trial may be considered relevant to a subject if they qualify or will qualify for a particular clinical trial. In some embodiments, each clinical trial may have a plurality of inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile.

In some embodiments, a clinical trial can be related to a subject if a threshold number of inclusion criteria is met by features of the subject profile. For example, a clinical trial may have a list of six inclusion criteria. Even though a subject that does not satisfy all six inclusion criteria may not be eligible to participate in a trial, if the subject satisfies a defined threshold number of six inclusion criteria (e.g., five), the clinical trial may be considered relevant to the subject. Thus, if only one or few criteria are not met, or if a subject fails to meet one or more criteria with a small defined margin, the clinical trial may be considered relevant to the subject and the treatment may be considered appropriate for the subject. In some embodiments, the exclusion criteria may be set such that if it falls within the exclusion criteria, the subject will not be able to participate in a particular trial. In some embodiments, the weights may be applied to the inclusion criteria. For example, some criteria may be weighted more heavily if they are considered more important (e.g., if they are considered more important to satisfy than other less important criteria). In some embodiments, the relevance of a clinical trial to a subject may be based on other factors, which may be included in the subject profile or may be considered in some other manner.

Each clinical trial in the set of clinical trials identified by the processor 102 corresponds to at least one treatment. In some embodiments, the clinical trial may correspond to a plurality of treatments. One or more treatments whose effectiveness in the trial may be considered to correspond to a clinical trial.

The processor 102 is further configured to rank the treatments corresponding to the relevant clinical trials. In other words, any treatment corresponding to a clinical trial in the identified set of clinical trials may be listed and ordered. For example, the treatments may be ranked or ordered according to one or more defined rules or criteria, as described below.

The processor 102 is also configured to output a ranking of treatments for the subject. For example, the processor 102 may output data indicating a ranking of treatments and/or may output a list of treatments in a ranked order. In some embodiments, the ranking may be output for presentation. For example, the ranking may be output to a display device, such as a display screen for presentation to a user. In this manner, a clinician may use the clinical support system 100 to obtain a ranked list of possible treatments corresponding to clinical trials related to their subjects. For example, due to the relevance of clinical trials that the subject may (or may have) qualified and the clinician (and/or subject) is not aware of, a ranked list may be used by the clinician to evaluate which treatments are most likely to help their subject.

The clinical trial in the set of clinical trials identified by the processor 102 may be a trial that was in progress at the time it was identified. However, while clinical trials are ongoing, there may be little information disclosed as to the success or effect of treatment in the trial. In some embodiments, the clinical trial identified by the processor 102 may be a trial that has occurred in the past and has been completed, terminated, or otherwise ended. In any case, the output data may be available from a clinical trial. In this manner, the system 100 can utilize information (e.g., output data) related to a clinical trial that is no longer active (i.e., in progress) for which significant and useful data is available, such as success rate of treatment, effectiveness measures of treatment, and side effects associated with treatment. By using information about a clinical trial that has provided output data (e.g., a completed or completed trial), a clinician can consider conducting a clinical trial on a treatment whose subject is unable to participate, even though they may meet inclusion criteria. For example, such a clinical trial can have been initiated (and possibly completed) before the subject was diagnosed with a particular medical condition that is likely to be relevant to the clinical trial.

As described above, the processor 102 may be configured to identify the set of clinical trials by searching a clinical trial database. In some embodiments, the clinical trials database may include at least clinical trials for which output data has been provided. For example, the clinical trial database may include trials that have ended. The clinical trials database may also include active or ongoing clinical trials.

According to some embodiments, the processor 102 may be configured to rank the treatments using a two-step process. In a first step, the processor 102 may rank the identified clinical trials. This may be considered a "coarse" or broad ranking step. In a second step, the processor 102 may rank the treatments according to a fine ranking or "fine tuning" step, as described below.

Thus, in order for the processor 102 to rank the treatments, the processor may be configured to rank the identified set of clinical trials. In some embodiments, the identified set of clinical trials may be ranked based on the clinical benefit achieved by each clinical trial. For example, clinical trials may be ranked in order of their realized clinical benefit. The clinical benefit achieved by a clinical trial may be defined by at least one of: a measure of progression-free survival of the participants in the clinical trial; a measure of overall survival of the participants in the clinical trial; and a measure of the participant's response rate in a clinical trial. A measure of progression-free survival of a subject is the length of time during and after treatment of the disease by therapy (e.g., in a clinical trial) in which the subject (e.g., a participant in the clinical trial) survives the disease without the disease deteriorating. A measure of overall survival is the length of time during and after treatment of the disease by therapy that the subject is still alive. The measure of response rate is the proportion of participants who exhibit a defined positive response (e.g., a defined amount of reduction in the size of the tumor) over a defined period of time. In some embodiments, the achieved clinical benefit may be measured as a comparison to a response from a standard of care (i.e., a standard recommended treatment). In other embodiments, other measures of clinical benefit of treatment may be used to rank clinical trials.

In some embodiments, in addition or alternatively to the above clinical trial ranking, the processor 102 may be configured to rank the identified set of clinical trials according to at least one of: similarity of a characteristic of the subject to a corresponding characteristic of a participant of the clinical trial; and the level of information available about the clinical trial. Thus, if a subject and a large number of participants in a particular clinical trial share a significant number of features with each other (e.g., features included in the subject profile and the profiles associated with the participants in the trial), the particular clinical trial can be ranked higher than a clinical trial in which the participants typically share fewer features with the subject. For some clinical trials, a large amount of information can be available about the trial itself and about the participants of the trial (e.g., can have been released after the trial was completed). However, in some cases, relatively more information may be available about the trial and its participants. Thus, differences in the amount of information (or granularity of information) available for clinical trials may be considered in the ranking. For example, a clinical trial for which a large amount of information is available may be ranked higher than a clinical trial for which relatively less information is available.

An initial (coarse) ranked list of clinical trials may be obtained according to the various clinical trial ranking techniques discussed above. The list may include clinical trials that, although related to a particular subject in terms of the criteria used above for ranking, may not be appropriate for that subject for other reasons. Thus, the initial list may also be modified by the processor 102 to obtain a more relevant list from which treatments may be selected for the subject. It should be noted that the step of ranking clinical trials discussed above (i.e., coarse ranking) may not be performed. In some embodiments, the processor 102 may derive treatments corresponding to the clinical trials in the list and rank the treatments using the techniques discussed below without first ranking the clinical trials.

In some embodiments, the processor 102 may be configured to rank the treatments based on the weighted scores. For example, some treatments may be considered more likely to lead to effective outcomes than others. In some embodiments, the weighted score may be based on one or more of the following: satisfaction score, outcome score, and complementary effect score.

The satisfaction score may indicate a degree of satisfaction with inclusion criteria of a plurality of features of the subject profile. Thus, treatments corresponding to clinical trials having a relatively large number of inclusion criteria met by the subject (i.e., features in the subject profile meet a large number of inclusion criteria) are given a relatively high weighted score.

The outcome score may indicate the extent to which each trial achieved clinical benefit. Thus, if a strong clinical benefit is achieved by the corresponding clinical trial, a relatively high weighted score may be given to the treatment. As noted above, clinical benefit may be defined by one or more of the following: a measure of progression-free survival of the participants in the clinical trial; a measure of overall survival of the participants in the clinical trial; and a measure of the participant's response rate in a clinical trial.

The supplemental effect score may indicate a measure of the expected side effects caused by each trial. Such side effects may include adverse events that occur as a result or consequence of the treatment in the trial. Side effects can be measured in terms of frequency and/or severity. For example, a relatively low weighted score may give treatment that is considered to cause significant side effects that occur frequently according to its corresponding clinical trial. The supplemental effect score may be referred to as a toxicity score or toxicity measure, as such a score relates to the toxicity and/or deleterious effects that can be caused to the subject.

After the "fine tuning" step of the ranking process, the ranked treatments can be adapted for viewing by the clinician and ranked in such a way that: a clinician may be able to quickly determine which treatment or treatments are best suited for a particular subject and may have the most positive clinical effect on that subject.

However, in some embodiments, the processor 102 may be configured to perform additional processing on the ranked treatments in order to generate an even more relevant treatment list. The processor 102 may be configured to group the ranked therapies according to at least one of: biological similarities between treatments; and similarities between features of the subject's profile and features of the profiles of the participants in the set of clinical trials. Thus, within the ranked list, treatments with biological similarities (e.g., treatments using the same drug or treatments targeting the same part of the body) may be grouped together. Similarly, treatments with corresponding clinical trials may be grouped together, where a large number of participants share common characteristics with the subject (e.g., characteristics in their profiles). By grouping certain treatments in the linked list, the clinician may be quickly able to determine those treatments and/or those clinical trials that are most relevant to the subject, as well as one or more reasons for the correlation.

In some embodiments, the processor 102 may be configured to identify treatments with corresponding clinical trials for which the subject almost met the inclusion criteria, but were undersized by less than a threshold amount (e.g., missed only one of the inclusion criteria). In this manner, the processor 102 may identify clinical trials that are related to the subject but in which the subject is not able to formally participate due to a failure to meet, for example, a relatively insignificant requirement. Subjects so close to meeting inclusion criteria may be expected to respond to treatment in a similar manner as participants in the corresponding clinical trial. Such a clinical trial may correspond to a treatment that is helpful to the subject but would not otherwise be considered by the clinician.

In some embodiments, the processor may be configured to remove one or more treatments from the ranked treatments if it fails to meet a particular defined criterion or defined requirement. For example, based on a subject profile, if it is deemed inappropriate for the subject, a particular treatment may be removed from the ranked list of treatments. This situation can occur, for example, if the treatment requires the application of a particular drug, but the subject profile indicates that the subject is allergic to the drug.

Once the treatment list has been ranked, it can be displayed to the clinician. The processor 102 may be configured to present the output ranked treatments to the user. The user may be, for example, a clinician. The ranked treatments and at least one of the following may be presented: the expected benefit of each presented treatment; and the potential risks associated with each presented treatment. In this way, a person viewing the presented list is able to quickly determine the potential strength of the treatment in terms of the clinical benefit that may be expected from each treatment, and the potential weakness of the treatment in terms of the potential risk that may arise from each treatment. The ranked treatments may be displayed on a display device associated with the system 100.

In some embodiments, the subject has cancer and the treatment comprises immunotherapy against cancer. By "immunotherapy" is meant any treatment that stimulates the immune system in order to treat a disease, for example in the case of cancer, immunotherapy is capable of stimulating the immune system to destroy or limit the growth of cancer cells. Thus, in such embodiments, the clinical trial involves an immunotherapy being tested for the treatment of cancer. The processor may be configured to rank the immunotherapy treatment selections (in addition to optionally further non-immunotherapy treatments) and output a ranking of the immunotherapy for the subject (and optionally further treatment selections). The present invention is particularly useful for identification due to the large number of immunotherapies currently undergoing clinical trials.

Fig. 2 shows an example of a system 100 that includes a processor 102 as well as a number of additional optional components. The system 100 of fig. 2 may include a user interface 202 and/or a display 204. The user interface 202 may be configured to receive user input, such as data representing a subject profile or clinical trial data. The display 204 may be configured to present ranked treatments to a user. The user interface 202 and/or display may be controlled by the processor 102.

The system 100 of fig. 2 may be connected to a clinical trials database 206, and the clinical trials database 206 may store clinical trials data used by the processor 102. The system 100 of fig. 2 may also be connected to a clinical database 208, and the clinical database 208 may store clinical data related to one or more subjects (i.e., subjects) for use by the processor 102. The clinical trial database 208 may include a description of each clinical trial, details of the inclusion criteria for each trial, the composition of the participants of each trial, information (e.g., profiles) about the participants of each trial, the treatment arm and distribution of participants on the trial arm for each trial, and the achieved clinical benefit relative to the criteria of care for each trial arm. It will be appreciated that connections to databases 206, 208 may be made using wired or wireless connections, and that the databases may be stored in storage media within system 100 or remote from the system.

According to another aspect, a method (e.g., a computer-implemented method) is provided. The method may be a method for ranking a plurality of treatments of a subject. The steps of the method may be performed by the processor 102 or by another processing device. Fig. 3 is a flow diagram of an example of a method 300 for ranking a plurality of treatments of a subject. The method includes, at step 302, establishing a subject profile for defining a subject based on a plurality of features. At step 304, the method 300 includes identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of a plurality of features of the profile of the subject. The method includes, at step 306, ranking the treatments corresponding to the relevant clinical trials. At step 308, the method 300 includes outputting a ranking of treatments for the subject. In general, the method may include any of the steps performed by the processor 102 discussed above.

Fig. 4 is a flow diagram of an example of a method 400 for ranking a plurality of treatments for a subject. Method 400 may include the steps of method 300. The method 400 may also include, at step 402, applying a weighted score to each treatment. In some embodiments, the ranking may be based on the applied weighted scores. In this way, as described above, more factors may be considered in evaluating the possible treatments available to the clinician to select for their subject.

In some embodiments, the weighted score may be based on at least one of: a satisfaction score indicating a degree of satisfaction of the inclusion criteria by a plurality of features of the subject profile; a result score indicating the extent to which each trial achieved clinical benefit; and a complementary effect score indicating a measure of the expected side effects caused by each test.

Fig. 5 is a flow diagram of an example of a method 500 for ranking a plurality of treatments for a subject. The method 500 may include the steps of: a subject profile is established (step 302), a set of clinical trials is identified (step 304), and treatments are ranked (step 306). In some embodiments, the step 306 of ranking the treatments may include, at step 502, ranking the identified set of clinical trials based on the clinical benefit achieved by each clinical trial. As mentioned above, the clinical benefit achieved by a clinical trial may be defined by at least one of: a measure of progression-free survival of the participants in the clinical trial; a measure of overall survival of the participants in the clinical trial; and a measure of the participant's response rate in a clinical trial.

In some embodiments, the method 500 may further include, at step 504, ranking the identified set of clinical trials according to at least one of: similarity of a subject feature to a corresponding feature of a participant in a clinical trial; and the level of information available about the clinical trial. The method 500 may continue by outputting (step 308) a ranking of the treatments. In embodiments where the clinical trial has no ranking (i.e., steps 502 and 504 are not performed), the method 500 may proceed to output the ranking (step 306).

By ranking the clinical trials according to steps 502 and 504, a user (e.g., a clinician) can obtain a list of treatments that can be adapted to a subject that have been coarsely ordered by relevance based on the factors considered in steps 502 and 504.

At step 506, the method 500 may include ranking the treatments based on the weighted scores. The weighted score may be based on at least one of: a satisfaction score indicating a degree of satisfaction of the inclusion criteria by a plurality of features of the subject profile; a result score indicating the extent to which each trial achieved clinical benefit; and a complementary effect score indicating a measure of the expected side effects caused by each test.

The method 500 may optionally include, at step 508, grouping the ranked treatments according to at least one of: biological similarities between treatments; and similarities between features of the subject profile and features of the profiles of the participants in the set of clinical trials.

At step 510, the output ranked treatments may be presented to the user. Treatments may be presented (at step 510) at one or more occasions during the method, such as: i) in the order in which it was output at step 308; ii) in the order in which they were output after their ranking based on the weighted scores at step 506; or iii) in the order in which they were output after their grouping at step 508. In some embodiments, the treatment may be presented (at step 510) in conjunction with at least one of: the expected benefit of each presented treatment; and the potential risks associated with each presented treatment. In some embodiments, the user may be provided with an opportunity to manually adjust one or more of the inclusion criteria of the clinical trial to see what effect such changes have on the output list. For example, the user may relax criteria, such as age range, to see which additional trials and corresponding treatments to add to the list. This may be of particular benefit, for example, if the list presented at step 510 is particularly short.

According to another aspect, a computer program product is provided. Fig. 6 is a simplified schematic diagram of a computer-readable medium 602 and a processor 604. According to some embodiments, the computer program product comprises a non-transitory computer-readable medium 602 having computer-readable code embodied therein, the computer-readable code being configured such that, when executed by a suitable computer or processor 604, the computer or processor is caused to perform any of the methods 300, 400, 500 disclosed herein. Processor 604 may include processor 102 or be similar to processor 102.

Processors 102, 604 may include one or more processors, processing units, multi-core processors, or modules configured or programmed to control devices and/or system 100 in the manner described herein. In particular embodiments, processors 102, 604 may include a plurality of software and/or hardware modules each configured to perform or be used to perform an individual step or steps of the methods described herein.

As used herein, the term "module" is intended to include a hardware component, such as a processor or a component of a processor configured to perform a particular function, or a software component, such as a set of instruction data having a particular function when executed by a processor.

It will be appreciated that embodiments of the invention also apply to computer programs, particularly computer programs on or in a carrier, adapted for putting the invention into practice. The program may take the form of source code, object code, a code intermediate source and object code such as partially compiled form, or in any other form suitable for use in the implementation of the method according to an embodiment of the invention. It will also be appreciated that such programs may have many different architectural designs. For example, program code implementing the functionality of the method or system according to the invention may be subdivided into one or more subroutines. Many different ways of distributing the functionality among these subroutines will be apparent to the skilled person. The subroutines may be stored together in an executable file to form a stand-alone program. Such an executable file may include computer-executable instructions, such as processor instructions and/or interpreter instructions (e.g., Java interpreter instructions). Alternatively, one or more or all of the subroutines may be stored in at least one external library file and linked to the main program either statically or dynamically (e.g., at runtime). The main program contains at least one call to at least one of the subroutines. The subroutines may also include function calls to each other. Embodiments relating to a computer program product include computer-executable instructions corresponding to each processing stage of at least one of the methods set forth herein. These instructions may be subdivided into subroutines and/or stored in one or more files that may be linked statically or dynamically. Another embodiment relating to a computer program product comprises computer-executable instructions corresponding to each module of at least one of the systems and/or products set forth herein. These instructions may be subdivided into subroutines and/or stored in one or more files that may be linked statically or dynamically.

The carrier of the computer program may be any entity or device capable of carrying the program. For example, the carrier may comprise a data storage device, such as a ROM, e.g. a CD ROM or a semiconductor ROM, or a magnetic recording medium, e.g. a hard disk. Further, the carrier may be a transmissible carrier such as an electrical or optical signal, which may be conveyed via electrical or optical cable or by radio or other means. When the program is embodied in such a signal, the carrier may be constituted by such cable or other device or module. Alternatively, the carrier may be an integrated circuit in which the program is embedded, the integrated circuit being adapted for performing, or for use in the performance of, the relevant method.

Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. A computer program may be stored/distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the internet or other wired or wireless telecommunication systems. Any reference signs in the claims shall not be construed as limiting the scope.

In a further aspect, the invention provides additional embodiments defined in the following numbered paragraphs:

1. a clinical decision support system (100) comprising:

a processor (102) configured to:

establishing an object profile for defining an object in accordance with a plurality of features;

identifying a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile;

ranking the treatments corresponding to the relevant clinical trials; and is

Outputting the ranking of the treatment for the subject.

2. The clinical decision support system (100) according to claim 1, wherein to rank the treatments, the processor (102) is configured to:

the identified set of clinical trials is ranked based on the clinical benefit achieved by each clinical trial.

3. The clinical decision support system (100) according to claim 2, wherein the processor (102) is configured to:

ranking the identified set of clinical trials according to at least one of: similarity of a feature of the subject to a corresponding feature of a participant of the clinical trial; and the level of information available about the clinical trial.

4. The clinical decision support system (100) according to claim 2 or claim 3, wherein the clinical benefit achieved by a clinical trial is defined by at least one of: a measure of progression-free survival of a participant in the clinical trial; a measure of overall survival of participants in the clinical trial; and a measure of the participant's response rate in the clinical trial.

5. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

ranking the treatments based on weighted scores.

6. The clinical decision support system (100) according to claim 5, wherein the weighted score is based on at least one of:

a satisfaction score that indicates a degree of satisfaction of the inclusion criteria by the plurality of features of the subject profile;

a result score indicating the extent to which each trial achieved clinical benefit; and

a complementary effect score indicating a measure of the expected side effects caused by each trial.

7. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

the subject profile is established by obtaining clinical information related to the subject from a clinical database (208).

8. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

the set of clinical trials is identified by searching a clinical trial database (206) that includes at least the clinical trials for which result data has been provided.

9. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

grouping the ranked treatments according to at least one of: biological similarities between the treatments; and similarities between features of the subject profile and features of profiles of participants in the set of clinical trials.

10. The clinical decision support system (100) according to any one of the preceding claims, wherein the processor (102) is configured to:

presenting the output ranked treatments to the user along with at least one of: the expected benefit of each presented treatment; and the potential risks associated with each presented treatment.

11. The clinical decision support system (100) according to any one of the preceding claims, wherein a clinical trial is related to the subject if a threshold number of inclusion criteria is met by features of the subject profile.

12. A method (300) for ranking a plurality of treatments for a subject, the method comprising:

establishing (302) an object profile defining an object according to a plurality of features;

identifying (304) a set of clinical trials associated with the subject, wherein each clinical trial in the set of associated clinical trials corresponds to at least one treatment and has inclusion criteria that are satisfied by a feature of the plurality of features of the subject profile;

ranking (306) the treatments corresponding to the relevant clinical trials; and is

Outputting (308) the ranking of the treatment for the subject.

13. The method (300, 400) of claim 12, further comprising:

applying (402) a weighted score to each therapy;

wherein the ranking (306) is based on the applied weighted score.

14. The method (300, 400) of claim 13, wherein the weighted score is based on at least one of:

a satisfaction score that indicates a degree of satisfaction of the inclusion criteria by the plurality of features of the subject profile;

a result score indicating the extent to which each trial achieved clinical benefit; and

a complementary effect score indicating a measure of the expected side effects caused by each trial.

15. A computer program product comprising a non-transitory computer-readable medium (602) having computer-readable code embodied therein, the computer-readable code being configured such that, on execution by a suitable computer or processor (604), the computer or processor is caused to perform the method of any of claims 12 to 14.