Personalized Multimorbidity Management for Patients with Type 2 Diabetes Using Reinforcement Learning of Electronic Health Records
BACKGROUND: Comorbid chronic conditions are common among people with type 2 diabetes. We developed an artificial intelligence algorithm, based on reinforcement learning (RL), for personalized diabetes and multimorbidity management, with strong potential to improve health outcomes relative to current clinical practice.
METHODS: We modeled glycemia, blood pressure, and cardiovascular disease (CVD) risk as health outcomes, using a retrospective cohort of 16,665 patients with type 2 diabetes from New York University Langone Health ambulatory care electronic health records in 2009-2017. We trained an RL prescription algorithm that recommends a treatment regimen optimizing patients' cumulative health outcomes using their individual characteristics and medical history at each encounter. The RL recommendations were evaluated on an independent subset of patients.
RESULTS: The single-outcome optimization RL algorithms, RL-glycemia, RL-blood pressure, and RL-CVD, recommended consistent prescriptions as that observed by clinicians in 86.1%, 82.9%, and 98.4% of the encounters, respectively. For patient encounters in which the RL recommendations differed from the clinician prescriptions, significantly fewer encounters showed uncontrolled glycemia (A1c > 8% in 35% of encounters), uncontrolled hypertension (blood pressure > 140 mmHg in 16% of encounters), and high CVD risk (risk > 20% in 25% of encounters) under RL algorithms compared with those observed under clinicians (43%, 27%, and 31% of encounters, respectively; all p < 0.001).
CONCLUSIONS: A personalized RL prescriptive framework for type 2 diabetes yielded high concordance with clinicians' prescriptions, and substantial improvements in glycemia, blood pressure, and CVD risk outcomes.
Errataetall: | |
---|---|
Medienart: |
E-Artikel |
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:81 |
---|---|
Enthalten in: |
Drugs - 81(2021), 4 vom: 11. März, Seite 471-482 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zheng, Hua [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 12.10.2021 Date Revised 12.10.2021 published: Print ErratumIn: Drugs. 2021 Feb 25;:. - PMID 33630279 Citation Status MEDLINE |
---|
doi: |
10.1007/s40265-020-01435-4 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM321307992 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM321307992 | ||
003 | DE-627 | ||
005 | 20231225175527.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s40265-020-01435-4 |2 doi | |
028 | 5 | 2 | |a pubmed24n1070.xml |
035 | |a (DE-627)NLM321307992 | ||
035 | |a (NLM)33570745 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zheng, Hua |e verfasserin |4 aut | |
245 | 1 | 0 | |a Personalized Multimorbidity Management for Patients with Type 2 Diabetes Using Reinforcement Learning of Electronic Health Records |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 12.10.2021 | ||
500 | |a Date Revised 12.10.2021 | ||
500 | |a published: Print | ||
500 | |a ErratumIn: Drugs. 2021 Feb 25;:. - PMID 33630279 | ||
500 | |a Citation Status MEDLINE | ||
520 | |a BACKGROUND: Comorbid chronic conditions are common among people with type 2 diabetes. We developed an artificial intelligence algorithm, based on reinforcement learning (RL), for personalized diabetes and multimorbidity management, with strong potential to improve health outcomes relative to current clinical practice | ||
520 | |a METHODS: We modeled glycemia, blood pressure, and cardiovascular disease (CVD) risk as health outcomes, using a retrospective cohort of 16,665 patients with type 2 diabetes from New York University Langone Health ambulatory care electronic health records in 2009-2017. We trained an RL prescription algorithm that recommends a treatment regimen optimizing patients' cumulative health outcomes using their individual characteristics and medical history at each encounter. The RL recommendations were evaluated on an independent subset of patients | ||
520 | |a RESULTS: The single-outcome optimization RL algorithms, RL-glycemia, RL-blood pressure, and RL-CVD, recommended consistent prescriptions as that observed by clinicians in 86.1%, 82.9%, and 98.4% of the encounters, respectively. For patient encounters in which the RL recommendations differed from the clinician prescriptions, significantly fewer encounters showed uncontrolled glycemia (A1c > 8% in 35% of encounters), uncontrolled hypertension (blood pressure > 140 mmHg in 16% of encounters), and high CVD risk (risk > 20% in 25% of encounters) under RL algorithms compared with those observed under clinicians (43%, 27%, and 31% of encounters, respectively; all p < 0.001) | ||
520 | |a CONCLUSIONS: A personalized RL prescriptive framework for type 2 diabetes yielded high concordance with clinicians' prescriptions, and substantial improvements in glycemia, blood pressure, and CVD risk outcomes | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Ryzhov, Ilya O |e verfasserin |4 aut | |
700 | 1 | |a Xie, Wei |e verfasserin |4 aut | |
700 | 1 | |a Zhong, Judy |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Drugs |d 1976 |g 81(2021), 4 vom: 11. März, Seite 471-482 |w (DE-627)NLM00001611X |x 1179-1950 |7 nnns |
773 | 1 | 8 | |g volume:81 |g year:2021 |g number:4 |g day:11 |g month:03 |g pages:471-482 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s40265-020-01435-4 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 81 |j 2021 |e 4 |b 11 |c 03 |h 471-482 |