Description:FORM 2

THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENT RULES, 2003

COMPLETE SPECIFICATION
(See Section 10 and Rule 13)

Title of invention:

SYSTEM AND METHOD FOR AUTOMATED COGNITIVE ENCODING OF INFORMATION BASED ON DOMAIN SPECIFIC STRATEGIES

Applicant
Tata Consultancy Services Limited
A company Incorporated in India under the Companies Act, 1956
Having address:
Nirmal Building, 9th floor,
Nariman point, Mumbai 400021,
Maharashtra, India

Preamble to the description:
The following specification particularly describes the invention and the manner in which it is to be performed.

TECHNICAL FIELD
[001] The disclosure herein generally relates to the field of pharmacovigilance & Materiovigilance and more specifically, to a method and system for an automated cognitive encoding of adverse events associated with the use of medicines and medical devices.

BACKGROUND
[002] Pharmacovigilance (PV) and Materiovigilance (MV) is defined as the process of medical product adverse event medical assessment. Currently PV and MV are highly dependent upon the experts . Increasing regulatory requirements and amount of Year-on-Year increasing volumes of product complaints and adverse events are adding to the overall pharmacovigilance efforts. Among the processes of pharmacovigilance, certain processes such as data entry and case creation are already handled by point automation to an extent. However, there is a scope of further automation using Artificial Intelligence (AI) in several aspects of the process.
[003] Coding of adverse events is a critical element and correctness of the coding overall has impact on various critical areas and hence requires critical consideration. As the medical products are used by both, technical and non-technical persons, the reports of product complaints have technical as well as plain language. Therefore, there is a diversity of the languages due to use of medical, technical, and plain or natural language. This diversity increases the complexity in medical coding of the product complaints on the medical dictionaries and even if this process is extremely logical, it requires a specific skill and mainly the trained physicians are engaged in the medical judgments or decisions.
[004] The major challenges in medical coding and causal assessment pertain to the difference between decision making process of the trained human brain and a trained AI instance. The natural language words may not correlate directly with a medical terms. This problem is more pronounced when the event is not a medical event but is a product technical issue or special circumstances related events. Often the meaningful information is not conveyed just by a word but by the entire statement of other information pertaining to the reported event or events. For a trained human brain, finding a medical code for a natural language term and then correlating it with the medical product effect is extremely obvious. This ability of brain pertains to its training, memory, and experience over a period of time and innumerable instances in various subjects. The input information diversity is not only limited to the language and dialects, but the basic information also has the changes.

SUMMARY
[005] Embodiments of the disclosure present technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method and system for an automated cognitive encoding of adverse events associated with the use of medicines and medical devices is provided.
[006] In one aspect, a processor-implemented method for an automated cognitive encoding of adverse events associated with the use of medicines and medical devices is provided. The processor-implemented method comprising receiving a primary information of a patient, collecting one or more statements from one or more stakeholders explaining administration of drugs to the patient, dosage of the drug administered, use of one or more medical devices, pre-processing, via one or more hardware processors, each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences associated with the administration of drugs and usage of medical devices, and analyzing, via one or more hardware processors, the identified one or more untoward occurrences (such as adverse events, technical issue with devices, special circumstances etc.) based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences to a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs, or medical devices.
[007] In another aspect, a system for an automated cognitive encoding of adverse events associated with the use of medicines and medical devices is provided. The system includes an input/output interface configured to receive a primary information of a patient, wherein the primary information comprising an age, a weight, and gender of the patient, one or more hardware processors and at least one memory storing a plurality of instructions, wherein the one or more hardware processors are configured to execute the plurality of instructions stored in the at least one memory.
[008] Further, the system is configured to collect one or more statements from one or more stakeholders explaining administration of drugs to the patient, dosage of the drug administered, use of one or more medical devices, pre-process each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences associated with the administration of drugs and usage of medical devices, and analyze the identified one or more untoward occurrences based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences in a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs, or medical devices
[009] In yet another aspect, one or more non-transitory machine-readable information storage mediums are provided comprising one or more instructions, which when executed by one or more hardware processors causes a method for an automated cognitive encoding of special events associated with the use of medicines and medical devices . The processor-implemented method comprising receiving a primary information of a patient, collecting one or more statements from one or more stakeholders explaining administration of drugs to the patient, dosage of the drug administered, use of one or more medical devices, pre-processing, via one or more hardware processors, each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences (such as adverse events, technical issue with devices, special circumstances etc.) associated with the administration of drugs and usage of medical devices, and analyzing, via one or more hardware processors, the identified one or more untoward occurrences based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences in a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs or medical devices.
[010] It is to be understood that the foregoing general descriptions and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
[011] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:
[012] FIG. 1 illustrates a block diagram of an exemplary system for an automated cognitive encoding of special events, in accordance with some embodiments of the present disclosure.
[013] FIG. 2 is a block diagram to illustrate the system for an automated cognitive encoding of special events, in accordance with some embodiments of the present disclosure.
[014] FIG. 3 is a flow diagram to illustrate a method for an automated cognitive encoding of special events, in accordance with some embodiments of the present disclosure.

DETAILED DESCRIPTION OF EMBODIMENTS
[015] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the scope of the disclosed embodiments.
[016] The embodiments herein provide a method and system for an automated cognitive encoding of special events associated with the use of medicines and medical devices. The major challenges in medical coding and causal assessment pertain to the difference between decision making process of the trained human brain and a trained AI instance. The natural language words may not correlate directly with a medical terms. Diversity of lingual terms and dialects, medical & technical language versus plain language wordings and variation in layman’s understanding of certain words are the major lingual factors limiting the process accuracy of medical coding. While technical/medical terms have their exact matches in the dictionaries/code-lists, plain or natural language requires multilevel processing. The available verbatim information requires conversion into meaningful statement(s) followed by finding of medical problem(s) there in. There is often a need to combine two or more statements to make one term or a diagnosis and removing duplicates without missing out on any piece of information.
[017] Also, depending upon the skill-set of the person and the source of information, the language used for reporting a product issue or a medical event has a wide diversity. The medical products users have different skills sets ranging from a lay-person to a specifically qualified medical practitioners, technicians, nurses, or pharmacists etc. In addition, the information is available in various formats, unformatted documents, and unstructured sources.
[018] There can be more than one linked or independent issues reported together. Often, a set of symptoms described in the verbatim may also lead to a nosological diagnosis, which actually makes the final event. Often the information obtained is non-specific and requires follow-up to complete the information. Mainly in case of laboratory reports, there is no connecting thread between abnormal values, where the diagnosis also includes clinical judgement.
[019] While triaging, case classification and validity assessment in Pharmacovigilance (PV) are already being considered for automation, medical coding, and assessment of causal relationship of the suspect product with the event are among the apt candidates for AI based automation. There are other processes having similarity of flow are insurance (claims and underwriting), healthcare reimbursements, medical billing, epidemiology etc. All these processes use medical coding and other such encoding. All these processes are principally the same, requiring the same skillset.
[020] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.
[021] FIG. 1 illustrates a block diagram of a system (100) for an automated cognitive encoding of special events associated with the use of medicines and medical devices, in accordance with an example embodiment. Although the present disclosure is explained considering that the system (100) is implemented on a server, it may be understood that the system (100) may comprise one or more computing devices (102), such as a laptop computer, a desktop computer, a notebook, a workstation, a cloud-based computing environment and the like. It will be understood that the system (100) may be accessed through one or more input/output interfaces 104-1, 104-2... 104-N, collectively referred to as I/O interface (104). Examples of the I/O interface (104) may include, but are not limited to, a user interface, a portable computer, a personal digital assistant, a handheld device, a smartphone, a tablet computer, a workstation, and the like. The I/O interface (104) are communicatively coupled to the system (100) through a network (106).
[022] In an embodiment, the network (106) may be a wireless or a wired network, or a combination thereof. In an example, the network (106) can be implemented as a computer network, as one of the different types of networks, such as virtual private network (VPN), intranet, local area network (LAN), wide area network (WAN), the internet, and such. The network (106) may either be a dedicated network or a shared network, which represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), and Wireless Application Protocol (WAP), to communicate with each other. Further, the network (106) may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices. The network devices within the network (106) may interact with the system (100) through communication links.
[023] The system (100) supports various connectivity options such as BLUETOOTH®, USB, ZigBee, and other cellular services. The network environment enables connection of various components of the system (100) using any communication link including Internet, WAN, MAN, and so on. In an exemplary embodiment, the system (100) is implemented to operate as a stand-alone device. In another embodiment, the system (100) may be implemented to work as a loosely coupled device to a smart computing environment. Further, the system (100) comprises at least one memory with a plurality of instructions, one or more databases (112), and one or more hardware processors (108) which are communicatively coupled with the at least one memory to execute a plurality of modules (114) therein. The components and functionalities of the system (100) are described further in detail.
[024] Herein, the one or more I/O interfaces (104) are configured to receive a primary information of a patient, wherein the primary information comprising age, and gender of the patient. Further, the system (100) is configured to collect one or more statements from one or more stakeholders explaining administering of drugs, dosage of the drug administered, use of medical devices, at least one indication/symptom, and special events associated with use of medical devices. Herein, the one or more stakeholders include the patient, an attendant, and a health professional.
[025] In one example, wherein an adverse event is reported that “my mid-section is bulging after having drug ABC’. The system (100) receives age of the patient, and dose of the drug consumed as input. Usually, the system (100) identifies whether the adverse event is due to drug or impact of any medical instrument. In the present example, it is a drug as mentioned in the given statement. The system (100) analyzes the statement using natural language processing to consider flow if any special event/circumstance have occurred. Tokens are then matched to produce medical procedures, surgeries, lab tests etc. further, the token are verified for precipitating factors. The precipitating factors initiate or promote the onset of any illness, disease, accident, or behavioral response. The tokens are then matched for sensation thesaurus. In this case, it matches with bulging, which is standardized to form of inflammation and increasing inflammation. The inputs from the matched vocabulary is processed, and combination searches are done on a processed, and harmonized dictionary (e.g. MedDRA). The searches are scored by the distance matches, to the terms. Finally, the system encodes to obesity and its related terms in the ontology.
[026] In one embodiment, the system (100) is configured to pre-process each of the one or more received statements using a cognitive natural language processing (NLP) to identify negation clauses, one or more health issues, context, procedure, precipitating factor, sensation, and location of the at least one adverse event/side effect. A rule engine of the system (100) is used to create rules based on deep domain understanding. The rule engine helps in prioritizing and chaining the rule execution, allowing implementation and execution of multiple, complex domains. The application of rules is recorded into logs for audits and traceability. Further, the rule engine is used to active/inactivate rules and to make changes to rules based on domain and/or regulatory changes. Chaining of rules allows deep nesting and effective rule identification and application.
[027] The rule engine is a series of ordered rules, that consider patient details, reporter details, drug information, dosage, intention etc. Based, on domain inputs, special circumstances/events are broken into different layers of rules. After the sentence is parsed, the rules are evaluated one by one, and considered for medical coding. There is use of symbols such as “*” or any, that refers to any combination of information. The symbols such as “!” indicate negation of the rule. As dictionaries get updated, rules are evaluated and updated as needed.
[028] Further, the system (100) is configured to standardized various words, phrases, and parts of speech to make them usable for the medical dictionary matching in an ontology based process. To understand a medical term, in addition to its context with respect to an event or special events. Multiple aspects need to be deciphered by the machine before processing.
[029] In another embodiment, the system (100) splits the one or more statements into clauses and automatically encodes the negations. It is to be noted that the negation is leading up to adjectives such as better and severe. Further, the system (100) matches the Lowest Level Term (LLT) vectors. Further, the one or more statements are pre-processed using the predefined NLP technique to determine special events. Firstly, the pre-processed one or more statements are analyzed to identify negation such as the drug didn’t work, my fever didn’t subside. Further, the system (100) checks the technical issues that are related to drug use, misuse, administrative usage etc.
[030] Referring FIG. 2, a block diagram (200), illustrating flow of information getting encoded to a medical event ontology, in accordance with some embodiments of the present disclosure. The one or more statements are passed through special circumstances and medical events process parallelly. Special circumstances are those events that are actual encodes but can’t be encoded by verbatim only, but also needs contextual knowledge. This contextual knowledge is driven by medical ontologies, company dictionaries, SME inputs, historical precedents etc.
[031] In another embodiment, the system (100) is configured to analyze the pre-processed each of the one or more statements based on predefined rules and a contextual knowledge to encode the at least one adverse event/side effect in a standardized vocabulary. The encoding comprising drugs, medical devices, and combination of both. The contextual knowledge is driven by medical ontologies, medical dictionaries, and historical precedents. Under special circumstances, firstly the system is configured to verify a negation such as the drug didn’t work, and my fever didn’t subside. Further, the system checks for technical issues, that are related to drug use, misuse, administrative usage etc. The technical issues are driven by different rules such as conditions, context, reporter details, usage conditions, administrative related state etc. Under medical events, the events are analyzed for procedure, precipitating factor, sensation, and location in order to come up with a holistic encoding. This is done using a combination of NLP, ontologies and dictionaries.
[032] For correct medical coding, the natural language terms as well as the rules need to be standardized for a correct and sustainable outcomes and improvisation. Hence, the natural language terms are standardized on basis of various dictionaries that are built manually and are enhanced by both, human, and machine. Similarly, a set of rules along with the hierarchy of their application in the data and the rule of stopping further process are standardized. The standardization of the dictionaries is a bilateral process, where the unique words in the code dictionaries and unique words in English dictionaries are standardized for each other. A bridging dictionary that covers inter-dictionary synonyms are also built and configured into the system (100).
[033] Referring FIG. 3, to illustrate a processor-implemented method (300) for an automated cognitive encoding of special events associated with the use of medicines and medical devices is provided. Medical coding is the transformation of healthcare diagnosis, procedures, medical services, and equipment into universal medical alphanumeric codes. The diagnoses and procedure codes are taken from medical record documentation, such as transcription of physician’s notes, laboratory, and radiologic results, etc. Accurate medical coding is important for billing and tracking statistics for disease and medical treatment.
[034] Initially, at step (302), receiving a primary information of a patient, wherein the primary information comprising an age, a weight, and gender of the patient.
[035] At the next step (304), collecting one or more statements from one or more stakeholders explaining administration of drugs to the patient, dosage of the drug administered, use of one or more medical devices.
[036] At the next step (306), pre-processing each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences associated with the administration of drugs and usage of medical devices.
[037] At the last step (308), analyzing the identified one or more untoward occurrences based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences in a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs or medical devices.
[038] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.
[039] The embodiments of present disclosure herein address the problem of medical coding and causal assessment pertain to the difference between decision making process of the trained human brain and a trained AI instance. The natural language words may not correlate directly with a medical terms. This problem is more pronounced when the event is not a medical event but is a product technical issue. Often the meaningful information is not conveyed just by a word but by the entire statement of a narrative.
[040] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g., any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g., hardware means like e.g., an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g., an ASIC and an FPGA, or at least one microprocessor and at least one memory with software modules located therein. Thus, the means can include both hardware means, and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g., using a plurality of CPUs.
[041] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[042] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.
[043] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[044] It is intended that the disclosure and examples be considered as exemplary only, with a true scope of disclosed embodiments being indicated by the following claims. , C , Claims:We Claim:
1. A processor-implemented method (300) comprising steps of:
receiving (302), via an input/output interface, a primary information of a patient, wherein the primary information comprising an age, a weight, and a gender of the patient;
collecting (304), via one or more hardware processors, one or more statements from one or more stakeholders, wherein the one or more statements explaining administration of drugs to the patient, dosage of the drug administered, and use of one or more medical devices;
pre-processing (306), via the one or more hardware processors, each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences associated with the administration of drugs and usage of medical devices; and
analyzing (308), via the one or more hardware processors, the identified one or more untoward occurrences based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences in a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs or medical devices.
2. The processor-implemented method (300) of claim 1, wherein the one or more stakeholders include the patient, an attendant to the patient, and a healthcare professional.
3. The processor-implemented method (300) of claim 1, wherein pre-processing identifies one or more negation clauses, one or more health issues, a context, a procedure, a precipitating factor, a sensation, and a location of the one or more untoward occurrences.
4. The processor-implemented method (300) of claim 1, wherein the contextual knowledge is driven by medical ontologies, medical dictionaries, and historical precedents.

5. A system (100) comprising:
an input/output interface (104) to receive a primary information of a patient, wherein the primary information comprising an age, a weight, and a gender of the patient;
a memory (110) in communication with the one or more hardware processors (108), wherein the one or more hardware processors (108) are configured to execute programmed instructions stored in the memory (110) to:
collect one or more statements from one or more stakeholders, wherein the one or more statements explaining administration of drugs to the patient, dosage of the drug administered, and use of one or more medical devices;
pre-process each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences associated with the administration of drugs and usage of medical devices; and
analyze the identified one or more untoward occurrences based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences in a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs or medical devices.
6. The system (100) of claim 5, wherein the one or more stakeholders include the patient, an attendant to the patient, and a healthcare professional.
7. The system (100) of claim 5, wherein pre-processing identifies one or more negation clauses, one or more health issues, a context, a procedure, a precipitating factor, a sensation, and a location of the one or more untoward occurrences.
8. The system (100) of claim 5, wherein the contextual knowledge is driven by medical ontologies, medical dictionaries, and historical precedents.
9. A non-transitory computer readable medium storing one or more instructions which when executed by one or more processors on a system, cause the one or more processors to perform method comprising:
receiving, via an input/output interface, a primary information of a patient, wherein the primary information comprising an age, a weight, and gender of the patient;
collecting, via the input/output interface, one or more statements from one or more stakeholders explaining administration of drugs to the patient, dosage of the drug administered, use of one or more medical devices;
pre-processing, via one or more hardware processors, each of the one or more received statements using a cognitive natural language processing (NLP) to identify one or more untoward occurrences associated with the administration of drugs and usage of medical devices; and
analyzing, via one or more hardware processors, the identified one or more untoward occurrences based on predefined rules and a contextual knowledge to encode the one or more untoward occurrences in a standardized vocabulary, wherein the encoding is done in terms of one or more of drugs or medical devices.

Dated this 7th Day of September 2022

Tata Consultancy Services Limited
By their Agent & Attorney

(Adheesh Nargolkar)
of Khaitan & Co
Reg No IN-PA-1086