Machine learning directed interventions associate with decreased hospitalization rates in hemodialysis patients. (September 2021)

• Record Type: Journal Article
• Authors: Chaudhuri, Sheetal; Han, Hao; Usvyat, Len; Jiao, Yue; Sweet, David; Vinson, Allison; Johnstone Steinberg, Stephanie; Maddux, Dugan; Belmonte, Kathleen; Brzozowski, Jane; Bucci, Brad; Kotanko, Peter; Wang, Yuedong; Kooman, Jeroen P.; Maddux, Franklin W.; Larkin, John
• Is Part Of: International journal of medical informatics. Volume 153(2021)
• Publication Date: 2021-09
• Subjects: Dialysis -- End stage kidney disease -- Hospitalization -- Mental health -- Nutrition -- Personalized care -- Interdisciplinary teams -- Social worker -- Psychosocial factors -- Behavioral health; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2021.104541
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: End Stage Kidney Disease patients have high rates of hospitalization. ML models can direct root cause evaluations and interventions in high-risk patients. ML based personalized interventions can improve hospitalization outcomes. Psychosocial barriers and structured behavioral health intervention can improve outcomes. ML models can be in integrated in clinical practice at the point of care to guide care teams. Abstract: Background: An integrated kidney disease company uses machine learning (ML) models that predict the 12-month risk of an outpatient hemodialysis (HD) patient having multiple hospitalizations to assist with directing personalized interdisciplinary interventions in a Dialysis Hospitalization Reduction Program (DHRP). We investigated the impact of risk directed interventions in the DHRP on clinic-wide hospitalization rates. Methods: We compared the hospital admission and day rates per-patient-year (ppy) from all hemodialysis patients in 54 DHRP and 54 control clinics identified by propensity score matching at baseline in 2015 and at the end of the pilot in 2018. We also used paired T test to compare the between group difference of annual hospitalization rate and hospitalization days rates at baseline and end of the pilot. Results: The between group difference in annual hospital admission and day rates was similar at baseline (2015) with a mean difference between DHRP versus control clinics of −0.008 ± 0.09 ppy and −0.05 ± 0.96 ppy respectively. The between group difference in hospital admission and day rates became more distinct at the end of follow up (2018) favoring DHRP clinics with the mean difference being −0.155 ± 0.38 ppy and −0.97 ± 2.78 ppy respectively. A paired t -test showed the change in the between group difference in hospital admission and day rates from baseline to the end of the follow up was statistically significant (t-value = 2.73, p-value < 0.01) and (t-value = 2.29, p-value = 0.02) respectively. Conclusions: These findings suggest ML model-based risk-directed interdisciplinary team interventions associate with lower hospitalization rates and hospital day rate in HD patients, compared to controls.