# US 12,014,816 B2 · Multi-sensor platform for health monitoring

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

- Number: US 12,014,816 B2
- Document ID: US12014816B2
- Status: Granted
- Kind: B2
- Application number: 17/130,534
- Filed: 2020-12-22
- Published: 2022-06-23
- Granted: 2024-06-18
- Earliest claimed: 2020-12-22
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: John Knickerbocker; Bing Dang; Qianwen Chen; Leanna Pancoast
- Web page: https://patentgrep.com/patent/US12014816B2

## CPC

- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- A61B 5/0022: {Monitoring a patient using a global network, e.g. telephone networks, internet}
- A61B 5/0024: {for multiple sensor units attached to the patient, e.g. using a body or personal area network}
- A61B 5/7264: {Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems}
- A61B 5/7275: {Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor}
- A61B 5/747: {in case of emergency, i.e. alerting emergency services}
- G06N 20/00: Machine learning
- G06Q 10/1093: Calendar-based scheduling for persons or groups
- G06Q 50/06: Energy or water supply
- G06Q 50/26: Government or public services (business processes related to the transportation industry G06Q50/40)
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 40/40: for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- H04L 9/32: including means for verifying the identity or authority of a user of the system {or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials}
- H04L 9/3231: {Biological data, e.g. fingerprint, voice or retina (network architectures or network communication protocols for supporting authentication of entities using biometrical features in a packet data network H04L63/0861)}
- A61B 5/021: Measuring pressure in heart or blood vessels
- A61B 5/02438: {with portable devices, e.g. worn by the patient}
- A61B 5/145: Measuring characteristics of blood in vivo, e.g. gas concentration or pH-value {; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid or cerebral tissue} (non-radiation detecting or locating of foreign bodies in blood A61B5/06)
- A61B 5/4842: {Monitoring progression or stage of a disease}
- A61B 5/4848: {Monitoring or testing the effects of treatment, e.g. of medication}
- A61B 5/7267: {involving training the classification device}
- A61B 2560/0204: of power management
- A61B 2560/0214: of power generation or supply
- H04L 2209/805: Lightweight hardware, e.g. radio-frequency identification [RFID] or sensor
- H04L 2209/88: Medical equipments
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A mechanism is provided in a data processing system to implement a multi-sensor health monitoring platform. The mechanism applies a machine learning model to predict patient needs and patient activity trends based on physiological features and activity features of the patient. The mechanism applies the machine learning model to predict energy requirements for a plurality of medical sensors based on the predicted patient needs and patient activity trends. The mechanism schedules recharging of the plurality of medical sensors based on the predicted energy requirements and identifying one or more sensors to set to an activate state based on the predicted patient needs and patient activity trends. The mechanism collecting sensor data from the one or more sensors and applies the machine learning model to generate a point-of-care recommendation based on the collected sensor data.

## Claims

### Claim 1

A method, in a data processing system comprising a processor and a memory, the memory comprising instructions that are executed by the processor to configure the processor to implement a multi-sensor health monitoring platform, the method comprising:
applying a machine learning model to predict patient needs and patient activity trends based on physiological features and activity features of the patient;
applying the machine learning model to predict energy requirements and energy availability for a plurality of medical sensors based on the predicted patient needs and patient activity trends, wherein the predicted energy requirements indicates an amount of energy needed to power a subset of medical sensors, of the plurality of medical sensors, to monitor at least one predicted patient need or activity at a future time point based on the predicted patient needs and patient activity trends, wherein the subset of medical sensors are medical sensors that monitor physiological features or activity features of the patient specific to the at least one predicted patient need or patient activity;
scheduling recharging of the subset of medical sensors, in the plurality of medical sensors, based on the predicted energy requirements and predicted energy availability of the subset of medical sensors, wherein the scheduling schedules recharging of the subset of medical sensors at a time point prior to the future time point such that the recharging causes at least one power source of the subset of medical sensors to have available electrical power to satisfy the predicted energy requirements at the future time point;
automatically controlling the plurality of medical sensors based on the predicted patient needs, patient activity trends, and predicted energy requirements, to set the subset of medical sensors to a recharge state in response to a current time being the time point prior to the future time point, to set the subset of medical sensors to an activate state in response to the current time being the future time point, and to set one or more other medical sensors in the subset of medical sensors to an inactive state in response to the current time being the future time point;
collecting sensor data from the subset of medical sensors in response to the current time being the future time point; and
applying the machine learning model to generate a point-of-care recommendation based on the collected sensor data.

### Claim 2 (depends on 1)

The method of claim 1, wherein the plurality of medical sensors comprise at least one of patient-worn sensors, non-wearable sensors, or internal sensors that are implanted in the patient.

### Claim 3 (depends on 1)

The method of claim 1, wherein applying the machine learning model to predict patient needs and patient activity trends comprises applying the machine learning model to patient history features for similar patients, and wherein applying the machine learning model to predict energy requirements for the plurality of medical sensors comprises applying the machine learning model to energy features of past energy usage of the plurality of medical sensors.

### Claim 4 (depends on 1)

The method of claim 1, wherein collecting the sensor data comprises tagging the sensor data with one or more sensor identifiers, a time stamp, and a patient identifier.

### Claim 5 (depends on 1)

The method of claim 1, wherein applying the machine learning model to generate the point-of-care recommendation comprises at least one of predicting whether an emergency event is occurring or scheduling a visit with a healthcare provider.

### Claim 6 (depends on 5)

The method of claim 5, further comprising contacting emergency services responsive to determining that an emergency event is occurring.

### Claim 7 (depends on 1)

The method of claim 1, further comprising applying the machine learning model to predict access to a communications device and scheduling transfer of the collected sensor data based on the predicted access to the communications device.

### Claim 8 (depends on 1)

The method of claim 1, further comprising training the machine learning model, through a machine learning training process based on historical data comprising data specifying past energy requirements of sensors, past energy levels of sensors, past predicted patient needs, and past predicted patient activity, to predict energy requirements.

### Claim 9 (depends on 8)

The method of claim 8, wherein the historical data comprises insight recommendations and outcomes relative to time for a one or more similar patients having characteristics similar to the patient, historical sensor data for the plurality of medical sensors associated with the patient, and patient health records for the patient and one or more similar patients.

### Claim 10 (depends on 1)

The method of claim 1, wherein scheduling recharging of the subset of medical sensors comprises selecting a recharge rate and the time point prior to the future time point for automatically initiating recharging of the subset of medical sensors.

### Claim 11 (depends on 1)

The method of claim 1, wherein the machine learning model learns which medical sensors in the plurality of medical sensors will be needed at different times of the day based on the patient activity trends and selects the learned medical sensors for inclusion in the subset of medical sensors.

### Claim 12 (depends on 1)

The method of claim 1, wherein scheduling recharging of the subset of medical sensors comprises predicting, by the machine learning model, when the patient will be physically in a location of a charger, and wherein the time point prior to the future time point is determined to be a time point when the patient will be physically in the location of the charger.

### Claim 13 (depends on 1)

The method of claim 1, wherein scheduling recharging of the subset of medical sensors comprises outputting a charging recommendation output to the patient with instructions to change a physical location of the patient to be within a range of a charger and to charge the subset of medical sensors.

### Claim 14 (depends on 1)

The method of claim 1, wherein the machine learning model comprises at least one first machine learning model that is trained to predict the patient needs and the patient activity trends based on the physiological features and the activity features of the patient and one or more similar patients having similar characteristics to the patient, and at least one second machine learning model, different from the at least one first machine learning model, that is trained to predict the energy requirements and energy availability for the plurality of medical sensors based on the predicted patient needs and patient activity trends.

### Claim 15

A computer program product comprising a non-transitory computer readable medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement a multi-sensor health monitoring platform, wherein the computer readable medium causes the computing device to:
apply a machine learning model to predict patient needs and patient activity trends based on physiological features and activity features of the patient;
apply the machine learning model to predict energy requirements and energy availability for a plurality of medical sensors based on the predicted patient needs and patient activity trends, wherein the predicted energy requirements indicates an amount of energy needed to power a subset of medical sensors, of the plurality of medical sensors, to monitor at least one predicted patient need or activity at a future time point based on the predicted patient needs and patient activity trends, wherein the subset of medical sensors are medical sensors that monitor physiological features or activity features of the patient specific to the at least one predicted patient need or patient activity;
schedule recharging of the subset of medical sensors, in the plurality of medical sensors, based on the predicted energy requirements and predicted energy availability of the subset of medical sensors, wherein the scheduling schedules recharging of the subset of medical sensors at a time point prior to the future time point such that the recharging causes at least one power source of the subset of medical sensors to have available electrical power to satisfy the predicted energy requirements at the future time point;
automatically controlling the plurality of medical sensors based on the predicted patient needs, patient activity trends, and predicted energy requirements, to set the subset of medical sensors to a recharge state in response to a current time being the time point prior to the future time point, to set the subset of medical sensors to an activate state in response to the current time being the future time point, and to set one or more other medical sensors in the subset of medical sensors to an inactive state in response to the current time being the future time point;
collect sensor data from the subset of medical sensors in response to the current time being the future time point; and
apply the machine learning model to generate a point-of-care recommendation based on the collected sensor data.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein applying the machine learning model to predict patient needs and patient activity trends comprises applying the machine learning model to patient history features for similar patients, and wherein applying the machine learning model to predict energy requirements for the plurality of medical sensors comprises applying the machine learning model to energy features of past energy usage of the plurality of medical sensors.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein the computer readable medium causes the computing device to apply the machine learning model to predict access to a communications device and scheduling transfer of the collected sensor data based on the predicted access to the communications device.

### Claim 18 (depends on 15)

The computer program product of claim 15, wherein scheduling recharging of the subset of medical sensors comprises predicting, by the machine learning model, when the patient will be physically in a location of a charger, and wherein the time point prior to the future time point is determined to be a time point when the patient will be physically in the location of the charger.

### Claim 19

An apparatus comprising:
a processor; and
a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement a multi-sensor health monitoring platform, wherein the instructions cause the processor to:
apply a machine learning model to predict patient needs and patient activity trends based on physiological features and activity features of the patient;
apply the machine learning model to predict energy requirements and energy availability for a plurality of medical sensors based on the predicted patient needs and patient activity trends, wherein the predicted energy requirements indicates an amount of energy needed to power a subset of medical sensors, of the plurality of medical sensors, to monitor at least one predicted patient need or activity at a future time point based on the predicted patient needs and patient activity trends, wherein the subset of medical sensors are medical sensors that monitor physiological features or activity features of the patient specific to the at least one predicted patient need or patient activity;
schedule recharging of the subset of medical sensors, in the plurality of medical sensors, based on the predicted energy requirements and predicted energy availability of the subset of medical sensors, wherein the scheduling schedules recharging of the subset of medical sensors at a time point prior to the future time point such that the recharging causes at least one power source of the subset of medical sensors to have available electrical power to satisfy the predicted energy requirements at the future time point;
automatically controlling the plurality of medical sensors based on the predicted patient needs, patient activity trends, and predicted energy requirements, to set the subset of medical sensors to a recharge state in response to a current time being the time point prior to the future time point, to set the subset of medical sensors to an activate state in response to the current time being the future time point, and to set one or more other medical sensors in the subset of medical sensors to an inactive state in response to the current time being the future time point;
collect sensor data from the subset of medical sensors in response to the current time being the future time point; and
apply the machine learning model to generate a point-of-care recommendation based on the collected sensor data.

### Claim 20 (depends on 19)

The apparatus of claim 19, wherein scheduling recharging of the subset of medical sensors comprises predicting, by the machine learning model, when the patient will be physically in a location of a charger, and wherein the time point prior to the future time point is determined to be a time point when the patient will be physically in the location of the charger.