# US 11,443,843 B2 · Personal customized guidance for treating patients

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,443,843 B2
- Document ID: US11443843B2
- Status: Granted
- Kind: B2
- Application number: 16/240,080
- Filed: 2019-01-04
- Published: 2020-07-09
- Granted: 2022-09-13
- Earliest claimed: 2019-01-04
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Anita Govindjee; Kai Liu; Su Liu; Manjunath Ravi
- Web page: https://patentgrep.com/patent/US11443843B2

## CPC

- G16H 20/60: relating to nutrition control, e.g. diets
- G16H 40/67: for remote operation
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 80/00: ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Approaches presented herein enable treating a medical condition via individual customized cognitive guidance. More specifically, a current interactive and customized diagnosis object (ICDO) comprising a treatment schedule for a patient is generated by combining a set of previous ICDOs from the patient, wherein each ICDO has a structure which defines elements that are used to diagnose a symptom and match the patient with a treatment. A status of the patient is monitored in real time via an internet of things network to detect an actual event of the patient differing from the treatment schedule. In real time, the treatment schedule is modified responsive to the differing event by adjusting the current ICDO by exchanging one element of the treatment plan for a new element according to a learned set of rules to compensate for the differing event. This modified treatment schedule is provided to the patient in real time.

## Claims

### Claim 1

A method for treating a medical condition via individual customized cognitive guidance, the method comprising:
generating a current interactive and customized diagnosis object (ICDO) comprising a treatment schedule for a patient by combining a set of previous ICDOs from the patient, wherein each ICDO has a structure which defines elements that are used to diagnose a symptom of the patient and match the patient with a treatment;
monitoring a status of the patient in real time via an internet of things network associated with the patient that automatically collects and enters patient status data into a current ICDO of the patient, the current ICDO comprising set of individual treatment technique preferences of the patient machine learned from historical events of the patient that differed and that complied with historic treatment schedules of the patient, the internet of things network comprising at least one wearable sensor that transmits data to the current ICDO through the network, the internet of things network being configured to detect an actual event of the patient differing from the treatment schedule, the actual event compromising an action by the patient that deviates from the treatment schedule, wherein some of the previous ICDOs from the patient are deleted over time as the patient makes progress with treatment of the medical condition, leaving a set of currently valid ICDOs from which the current ICDO is derived;
modifying, in real time, the treatment schedule responsive to the differing event by adjusting the current ICDO of the patient according to a learned set of rules derived from the set of currently valid ICDOs to compensate for the differing event, the learned set of rules comprising the set of individual treatment technique preferences of the patient and, the adjusting comprising exchanging one element of the treatment schedule for a new element compromising an action by the patient that brings the patient into alignment with a net effect of the initial treatment schedule, the exchanged element being optimized for treatment effectiveness, patient comfort, and historical successfulness based on the treatment technique preferences of the patient; and
providing the modified treatment schedule to the patient in real time.

### Claim 2 (depends on 1)

The method of claim 1, the method further comprising:
creating automatically an initial ICDO for the patient;
monitoring a real-time status of the patient via the internet of things network associated with the patient;
generating automatically, responsive to the monitoring, a set of ICDOs updating the initial ICDO for the patient; and
generating the set of rules customized to the patient from a set of symptom patterns and a set of treatment patterns learned from adjustments by a professional to the set of ICDOs during a machine learning phase.

### Claim 3 (depends on 2)

The method of claim 2, the machine learning phase comprising:
providing a configuration user interface for controlling and managing a real-time intervention service from a human user; and
receiving a manual update to an ICDO of the set of ICDOs from a human who is monitoring symptoms of the patient and progress of the patient over time.

### Claim 4 (depends on 1)

The method of claim 1, the learned set of rules comprising instructions to create a new treatment plan responsive to a progress of the patient not meeting a predetermined threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein the actual event is an actual eating event and the treatment schedule is a scheduled eating plan and wherein the method further comprises:
rating a severity level of the actual eating event of the user by comparing the actual eating event to a set of eating events in the scheduled eating plan for the patient; and
updating the scheduled eating plan for the patient based on the severity level of the actual eating event.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
tracking patient activity, nutrition, and eating behavior over time;
creating a diagnosis scheme to determine symptom severity, divided by behavior at each meal;
defining a framework and related algorithms for supporting a real-time scheme filter;
tracking historical symptom and treatment plan records against learned professional diagnoses; and
developing a cognitive symptom and treatment pattern repository over time.

### Claim 7 (depends on 1)

The method of claim 1, each ICDO comprising a physical description of the patient, activity of the patient, a scheduled eating plan for the patient, and a set of actual eating events of the patient.

### Claim 8 (depends on 7)

The method of claim 7, wherein the scheduled eating plan for the patient comprises a list of a plurality of foods and portions the patient should eat at predetermined times during a day, and wherein the set of actual eating events of the patient comprises a list of a plurality of foods and portions the patient actually ate, an eating quantity rating, an eating schedule value, and an eating severity level value.

### Claim 9

A computer system for treating a medical condition via individual customized cognitive guidance, the computer system comprising:
a memory medium comprising program instructions;
a bus coupled to the memory medium; and
a processor, for executing the program instructions, coupled to a cognitive and customized assistant engine via the bus that when executing the program instructions causes the system to:
generate a current interactive and customized diagnosis object (ICDO) comprising a treatment schedule for a patient by combining a set of previous ICDOs from the patient, wherein each ICDO has a structure which defines elements that are used to diagnose a symptom of the patient and match the patient with a treatment;
monitor a status of the patient in real time via an internet of things network associated with the patient that automatically collects and enters patient status data into a current ICDO of the patient, the current ICDO comprising set of individual treatment technique preferences of the patient machine learned from historical events of the patient that differed and that complied with historic treatment schedules of the patient, the internet of things network comprising at least one wearable sensor that transmits data to the current ICDO through the network, the internet of things network being configured to detect an actual event of the patient differing from the treatment schedule, the actual event compromising an action by the patient that deviates from the treatment schedule, wherein some of the previous ICDOs from the patient are deleted over time as the patient makes progress with treatment of the medical condition, leaving a set of currently valid ICDOs from which the current ICDO is derived;
modify, in real time, the treatment schedule responsive to the differing event by adjusting the current ICDO of the patient according to a learned set of rules derived from the set of currently valid ICDOs to compensate for the differing event, the learned set of rules comprising the set of individual treatment technique preferences of the patient and, the adjusting comprising exchanging one element of the treatment schedule for a new element compromising an action by the patient that brings the patient into alignment with a net effect of the initial treatment schedule, the exchanged element being optimized for treatment effectiveness, patient comfort, and historical successfulness based on the treatment technique preferences of the patient; and
provide the modified treatment schedule to the patient in real time.

### Claim 10 (depends on 9)

The computer system of claim 9, the instructions further causing the system to:
create automatically an initial ICDO for the patient;
monitor a real-time status of the patient via the internet of things network associated with the patient;
generate automatically, responsive to the monitoring, a set of ICDOs updating the initial ICDO for the patient; and
generate the set of rules customized to the patient from a set of symptom patterns and a set of treatment patterns learned from adjustments by a professional to the set of ICDOs during a machine learning phase.

### Claim 11 (depends on 9)

The computer system of claim 9, the learned set of rules comprising instructions to create a new treatment plan responsive to a progress of the patient not meeting a predetermined threshold.

### Claim 12 (depends on 9)

The computer system of claim 9, the actual event being an actual eating event and the treatment schedule being a scheduled eating plan, and the instructions further causing the system to:
rate a severity level of the actual eating event of the user by comparing the actual eating event to a set of eating events in the scheduled eating plan for the patient; and
update the scheduled eating plan for the patient based on the severity level of the actual eating event.

### Claim 13 (depends on 9)

The computer system of claim 9, the instructions further causing the system to:
track patient activity, nutrition, and eating behavior over time;
create a diagnosis scheme to determine symptom severity, divided by behavior at each meal;
define a framework and related algorithms for supporting a real-time scheme filter;
track historical symptom and treatment plan records against learned professional diagnoses; and
develop a cognitive symptom and treatment pattern repository over time.

### Claim 14 (depends on 9)

The computer system of claim 9, wherein each ICDO comprises a physical description of the patient, activity of the patient, a scheduled eating plan for the patient, and a set of actual eating events of the patient, and wherein the scheduled eating plan for the patient comprises a list of a plurality of foods and portions the patient should eat at predetermined times during a day, and wherein the set of actual eating events of the patient comprises a list of a plurality of foods and portions the patient actually ate, an eating quantity rating, an eating schedule value, and an eating severity level value.

### Claim 15

A computer program product for treating a medical condition via individual customized cognitive guidance, the computer program product comprising a computer readable hardware storage device, and program instructions stored on the computer readable hardware storage device, to:
generate a current interactive and customized diagnosis object (ICDO) comprising a treatment schedule for a patient by combining a set of previous ICDOs from the patient, wherein each ICDO has a structure which defines elements that are used to diagnose a symptom of the patient and match the patient with a treatment;
monitor a status of the patient in real time via an internet of things network associated with the patient that automatically collects and enters patient status data into a current ICDO of the patient, the current ICDO comprising set of individual treatment technique preferences of the patient machine learned from historical events of the patient that differed and that complied with historic treatment schedules of the patient, the internet of things network comprising at least one wearable sensor that transmits data to the current ICDO through the network, the internet of things network being configured to detect an actual event of the patient differing from the treatment schedule, the actual event compromising an action by the patient that deviates from the treatment schedule, wherein some of the previous ICDOs from the patient are deleted over time as the patient makes progress with treatment of the medical condition, leaving a set of currently valid ICDOs from which the current ICDO is derived;
modify, in real time, the treatment schedule responsive to the differing event by adjusting the current ICDO of the patient according to a learned set of rules derived from the set of currently valid ICDOs to compensate for the differing event, the learned set of rules comprising the set of individual treatment technique preferences of the patient and, the adjusting comprising exchanging one element of the treatment schedule for a new element compromising an action by the patient that brings the patient into alignment with a net effect of the initial treatment schedule, the exchanged element being optimized for treatment effectiveness, patient comfort, and historical successfulness based on the treatment technique preferences of the patient; and
provide the modified treatment schedule to the patient in real time.

### Claim 16 (depends on 15)

The computer program product of claim 15, the computer readable storage device further comprising instructions to:
create automatically an initial ICDO for the patient;
monitor a real-time status of the patient via the internet of things network associated with the patient;
generate automatically, responsive to the monitoring, a set of ICDOs updating the initial ICDO for the patient; and
generate the set of rules customized to the patient from a set of symptom patterns and a set of treatment patterns learned from adjustments by a professional to the set of ICDOs during a machine learning phase.

### Claim 17 (depends on 15)

The computer program product of claim 15, the learned set of rules comprising instructions to create a new treatment plan responsive to a progress of the patient not meeting a predetermined threshold.

### Claim 18 (depends on 15)

The computer program product of claim 15, the actual event being an actual eating event and the treatment schedule being a scheduled eating plan, and the computer readable storage device further comprising instructions to:
rate a severity level of the actual eating event of the user by comparing the actual eating event to a set of eating events in the scheduled eating plan for the patient; and
update the scheduled eating plan for the patient based on the severity level of the actual eating event.

### Claim 19 (depends on 15)

The computer program product of claim 15, the computer readable storage device further comprising instructions to:
track patient activity, nutrition, and eating behavior over time;
create a diagnosis scheme to determine symptom severity, divided by behavior at each meal;
define a framework and related algorithms for supporting a real-time scheme filter;
track historical symptom and treatment plan records against learned professional diagnoses; and
develop a cognitive symptom and treatment pattern repository over time.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein each ICDO comprises a physical description of the patient, activity of the patient, a scheduled eating plan for the patient, and a set of actual eating events of the patient, and wherein the scheduled eating plan for the patient comprises a list of a plurality of foods and portions the patient should eat at predetermined times during a day, and wherein the set of actual eating events of the patient comprises a list of a plurality of foods and portions the patient actually ate, an eating quantity rating, an eating schedule value, and an eating severity level value.