Predicting 90 day acute heart failure readmission and death using machine learning‐supported decision analysis

Abstract

Readmission or death soon after heart failure (HF) admission is a significant problem. Traditional analyses for predicting such events often fail to consider the gamut of characteristics that may contribute– tending to focus on 30‐day outcomes even though the window of increased vulnerability may last up to 90 days. Risk assessments incorporating machine learning (ML) methods may be better suited than traditional statistical analyses alone to sort through multitude of data in the electronic health record (EHR) and identify patients at higher risk. Hypothesis ML‐based decision analysis may better identify patients at increased risk for 90‐day acute HF readmission or death after incident HF admission. Methods and Results Among 3189 patients who underwent index HF hospitalization, 15.2% experienced primary or acute HF readmission and 11.5% died within 90 days. For risk assessment models, 98 variables were considered across nine data categories. ML techniques were used to help select variables for a final logistic regression (LR) model. The final model's AUC was 0.760 (95% CI 0.752 to 0.767), with sensitivity of 83%. This proved superior to an LR model alone [AUC 0.744 (95% CI 0.732 to 0.755)]. Eighteen variables were identified as risk factors including dilated inferior vena cava, elevated blood pressure, elevated BUN, reduced albumin, abnormal sodium or bicarbonate, and NT pro‐BNP elevation. A risk prediction ML‐based model developed from comprehensive characteristics within the EHR can efficiently identify patients at elevated risk of 90‐day acute HF readmission or death for whom closer follow‐up or further interventions may be considered.

Predicting hospital readmission risk in patients with COVID-19: A machine learning approach

“…So far, most previous ML-based studies have focused on predicting readmission of chronic conditions such as cardiovascular [ 1 , [34] , [35] , [36] , [37] , [38] , [39] ], stroke [ [40] , [41] , [42] , [43] , [44] ], and COPD [ 5 , 6 , [45] , [46] , [47] ]. Till now, few studies have been conducted about COVID-19 readmission.…”

Machine Learning Patient-Specific Prediction of Heart Failure Hospitalization Using Cardiac MRI-Based Phenotype and Electronic Health Information

“…All have struggled to achieve the performance of models trained to predict mortality ( 29 , 30 ), suggesting elevated need to consider patient-specific disease phenotypes. The latter concept was explored in a study of 3,189 HF in-patients where multi-domain phenotypic data, gathered from routine echocardiography reporting, enabled prediction of all-cause early re-hospitalization with higher predictive accuracy than prior administrative data supported models, achieving an AUC of 0.76 at 90-days ( 31 ). While demonstrating value from multi-domain imaging phenotypes, this study was limited to high-risk inpatient populations, preventing generalizability to those patients routinely encountered by diagnostic imaging services.…”

Tailored risk assessment of 90‐day acute heart failure readmission or all‐cause death to heart failure with preserved versus reduced ejection fraction

“…The primary outcome was a composite outcome of acute HF readmission or all‐cause mortality within 90 days after discharge from an index HF hospitalization. Acute HF readmission was identified by any of the following: (1) primary HF diagnosis, (2) secondary HF diagnosis denoting acuity (with previously described diagnostic codes) or (3) secondary HF diagnostic codes of any acuity along with documentation of intravenous diuretic administration 18 . In patients who experienced multiple events within the 90‐day window such as HF readmission and death, only the first event was counted.…”

“…Inclusion and exclusion criteria, including qualifying ICD codes, were described previously. 18 For this unique analysis, patients were classified according to HF subtypes, as either having HFpEF (LVEF ≥ 50%) or HFrEF (LVEF < 50%), based on ejection fraction.…”

“…In this study, we developed the UF 90‐day post‐discharge acute HF Readmission or Death Risk Assessment (UF90‐RADRA) models tailored to HF subtype. Building upon our previous effort to develop a generic HF risk prediction model, we improved the study design by incorporating more variables and developing models specific to HFpEF and HFrEF subtypes with the goal of identifying patients at elevated 90‐day risk of acute HF readmission or all‐cause mortality at the time of discharge 18 . Identifying such high‐risk patients at the point of discharge is critical to anticipating the need for additional support for these patients.…”