# US 12,112,296 B2 · High fidelity clinical documentation improvement (CDI) smart scoring systems and methods

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

- Number: US 12,112,296 B2
- Document ID: US12112296B2
- Status: Granted
- Kind: B2
- Application number: 18/450,946
- Filed: 2023-08-16
- Published: 2023-12-07
- Granted: 2024-10-08
- Earliest claimed: 2016-11-11
- Assignees: Iodine Software, LLC
- Applicants: Iodine Software, LLC
- Inventors: William Chan; W. Lance Eason; Timothy Harper; Bryan Horne; Michael Kadyan; Jonathan Matthews; Joshua Toub
- Web page: https://patentgrep.com/patent/US12112296B2

## CPC

- G06Q 10/10: Office automation; Time management
- G06N 3/09: Supervised learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G06Q 50/22: Social work or social welfare, e.g. community support activities or counselling services
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G16H 40/67: for remote operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A clinical documentation improvement (CDI) smart scoring method may include predicting, via per-condition diagnosis machine learning (ML) models and based on clinical evidence received by a system, a probability that a medical condition is under-documented and, via per-condition documentation ML models and based on documentation received by the system, a probability that a medical condition is over-documented. The under- and over-documentation scores are combined in view of special indicators and queryability factors, which can also be evaluated using ML query prediction models, to generate an initial CDI score. This CDI score can be further adjusted, if necessary or desired, to account for factors such as length of stay, payer, patient location, CDI review timing, etc. The final CDI score can be used to prioritize patient cases for review by CDI specialists to quickly and efficiently identify meaningful CDI opportunities.

## Claims

### Claim 1

A method, comprising:
receiving, by a clinical documentation improvement (CDI) system, real-time medical data from a data source, the real-time medical data comprising clinical data for a patient and documentation for a visit of the patient;
determining, by the CDI system based on the real-time medical data, a medical condition for the patient;
determining, by the CDI system utilizing the real-time medical data, a difference between portions of the real-time medical data and stored data items the CDI system has for the visit of the patient;
applying, by the CDI system, a machine learning diagnosis model to the portions of the real-time medical data to generate an under-documentation score, the under-documentation score representing a probability that the medical condition is clinically valid but is not sufficiently documented;
applying, by the CDI system, a machine learning documentation model to the stored data items the CDI system has for the visit of the patient to generate an over-documentation score, the over-documentation score representing a probability that the medical condition is documented but is not supported by the clinical data for the patient; and
generating, by the CDI system based at least in part on the under-documentation score and the over-documentation score, a CDI score for the visit of the patient.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
determining special indicators applicable to the visit of the patient, wherein the special indicators represent significant events during the visit of the patient;
aggregating values of the special indicators; and
generating a special indicators score based on the values of the special indicators thus aggregated, wherein generating the CDI score for the visit of the patient further includes combining the under-documentation score for the medical condition, the over-documentation score for the medical condition, and the special indicators score.

### Claim 3 (depends on 2)

The method of claim 2, wherein the special indicators score is independent of the under-documentation score for the medical condition, the over-documentation score for the medical condition, or a combination thereof.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
evaluating the under-documentation score for the medical condition in conjunction with a queryability factor that represents a consideration applicable to the visit of the patient; and
determining an overall under-documentation score based at least in part on the evaluating.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
aggregating over-documentation scores across medical conditions in the data set for the visit of the patient; and
generating an overall over-documentation score based on the over-documentation scores thus aggregated.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
determining a cumulative probability that the medical condition determined from the real-time medical data is an undocumented complication or comorbidity, the determining the cumulative probability based at least in part on information about the patient, a number of progress notes by an attending physician for the patient, a number of queries made to the stored data items the CDI system has for the visit of the patient, or a count of undocumented medical conditions found in the stored data items the CDI system has for the visit of the patient.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
adjusting the CDI score for the visit of the patient based at least in part on a location of the patient.

### Claim 8

A clinical documentation improvement (CDI) system, comprising:
a processor;
a non-transitory computer readable medium; and
stored instructions translatable by the processor to perform:
receiving real-time medical data from a data source, the real-time medical data comprising clinical data for a patient and documentation for a visit of the patient;
determining, based on the real-time medical data, a medical condition for the patient;
determining, utilizing the real-time medical data, a difference between portions of the real-time medical data and stored data items the CDI system has for the visit of the patient;
applying a machine learning diagnosis model to the portions of the real-time medical data to generate an under-documentation score, the under-documentation score representing a probability that the medical condition is clinically valid but is not sufficiently documented;
applying a machine learning documentation model to the stored data items the CDI system has for the visit of the patient to generate an over-documentation score, the over-documentation score representing a probability that the medical condition is documented but is not supported by the clinical data for the patient; and
generating, based at least in part on the under-documentation score and the over-documentation score, a CDI score for the visit of the patient.

### Claim 9 (depends on 8)

The CDI system of claim 8, wherein the stored instructions are further translatable by the processor to perform:
determining special indicators applicable to the visit of the patient, wherein the special indicators represent significant events during the visit of the patient;
aggregating values of the special indicators; and
generating a special indicators score based on the values of the special indicators thus aggregated, wherein generating the CDI score for the visit of the patient further includes combining the under-documentation score for the medical condition, the over-documentation score for the medical condition, and the special indicators score.

### Claim 10 (depends on 9)

The CDI system of claim 9, wherein the special indicators score is independent of the under-documentation score for the medical condition, the over-documentation score for the medical condition, or a combination thereof.

### Claim 11 (depends on 8)

The CDI system of claim 8, wherein the stored instructions are further translatable by the processor to perform:
evaluating the under-documentation score for the medical condition in conjunction with a queryability factor that represents a consideration applicable to the visit of the patient; and
determining an overall under-documentation score based at least in part on the evaluating.

### Claim 12 (depends on 8)

The CDI system of claim 8, wherein the stored instructions are further translatable by the processor to perform:
aggregating over-documentation scores across medical conditions in the data set for the visit of the patient; and
generating an overall over-documentation score based on the over-documentation scores thus aggregated.

### Claim 13 (depends on 8)

The CDI system of claim 8, wherein the stored instructions are further translatable by the processor to perform:
determining a cumulative probability that the medical condition determined from the real-time medical data is an undocumented complication or comorbidity, the determining the cumulative probability based at least in part on information about the patient, a number of progress notes by an attending physician for the patient, a number of queries made to the stored data items the CDI system has for the visit of the patient, or a count of undocumented medical conditions found in the stored data items the CDI system has for the visit of the patient.

### Claim 14 (depends on 8)

The CDI system of claim 8, wherein the stored instructions are further translatable by the processor to perform:
adjusting the CDI score for the visit of the patient based at least in part on a location of the patient.

### Claim 15

A computer program product comprising a non-transitory computer-readable medium storing instructions translatable by a processor of a clinical documentation improvement (CDI) system to perform:
receiving real-time medical data from a data source, the real-time medical data comprising clinical data for a patient and documentation for a visit of the patient;
determining, based on the real-time medical data, a medical condition for the patient;
determining, utilizing the real-time medical data, a difference between portions of the real-time medical data and stored data items the CDI system has for the visit of the patient;
applying a machine learning diagnosis model to the portions of the real-time medical data to generate an under-documentation score, the under-documentation score representing a probability that the medical condition is clinically valid but is not sufficiently documented;
applying a machine learning documentation model to the stored data items the CDI system has for the visit of the patient to generate an over-documentation score, the over-documentation score representing a probability that the medical condition is documented but is not supported by the clinical data for the patient; and
generating, based at least in part on the under-documentation score and the over-documentation score, a CDI score for the visit of the patient.

### Claim 16 (depends on 15)

The computer program product of claim 15, wherein the instructions are further translatable by the processor to perform:
determining special indicators applicable to the visit of the patient, wherein the special indicators represent significant events during the visit of the patient;
aggregating values of the special indicators; and
generating a special indicators score based on the values of the special indicators thus aggregated, wherein generating the CDI score for the visit of the patient further includes combining the under-documentation score for the medical condition, the over-documentation score for the medical condition, and the special indicators score.

### Claim 17 (depends on 15)

The computer program product of claim 15, wherein the special indicators score is independent of the under-documentation score for the medical condition, the over-documentation score for the medical condition, or a combination thereof.

### Claim 18 (depends on 15)

The computer program product of claim 15, wherein the instructions are further translatable by the processor to perform:
evaluating the under-documentation score for the medical condition in conjunction with a queryability factor that represents a consideration applicable to the visit of the patient; and
determining an overall under-documentation score based at least in part on the evaluating.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein the instructions are further translatable by the processor to perform:
aggregating over-documentation scores across medical conditions in the data set for the visit of the patient; and
generating an overall over-documentation score based on the over-documentation scores thus aggregated.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein the instructions are further translatable by the processor to perform:
determining a cumulative probability that the medical condition determined from the real-time medical data is an undocumented complication or comorbidity, the determining the cumulative probability based at least in part on information about the patient, a number of progress notes by an attending physician for the patient, a number of queries made to the stored data items the CDI system has for the visit of the patient, or a count of undocumented medical conditions found in the stored data items the CDI system has for the visit of the patient.