Comparison of machine learning and conventional statistical modeling for predicting readmission following acute heart failure hospitalization.

INTRODUCTION: Developing accurate models for predicting the risk of 30-day readmission is a major healthcare interest. Evidence suggests that models developed using machine learning (ML) may have better discrimination than conventional statistical models (CSM), but the calibration of such models is unclear. OBJECTIVES: To compare models developed using ML with those developed using CSM to predict 30-day readmission for cardiovascular and noncardiovascular causes in HF patients. METHODS: We retrospectively enrolled 10,919 patients with HF (> 18 years) discharged alive from a hospital or emergency department (2004-2007) in Ontario, Canada. The study sample was randomly divided into training and validation sets in a 2:1 ratio. CSMs to predict 30-day readmission were developed using Fine-Gray subdistribution hazards regression (treating death as a competing risk), and the ML algorithm employed random survival forests for competing risks (RSF-CR). Models were evaluated in the validation set using both discrimination and calibration metrics. RESULTS: In the validation sample of 3602 patients, RSF-CR (c-statistic=0.620) showed similar discrimination to the Fine-Gray competing risk model (c-statistic=0.621) for 30-day cardiovascular readmission. In contrast, for 30-day noncardiovascular readmission, the Fine-Gray model (c-statistic=0.641) slightly outperformed the RSF-CR model (c-statistic=0.632). For both outcomes, The Fine-Gray model displayed better calibration than RSF-CR using calibration plots of observed vs predicted risks across the deciles of predicted risk. CONCLUSIONS: Fine-Gray models had similar discrimination but superior calibration to the RSF-CR model, highlighting the importance of reporting calibration metrics for ML-based prediction models. The discrimination was modest in all readmission prediction models regardless of the methods used.

Functional impact of pediatric postthrombotic syndrome.

BACKGROUND: Postthrombotic syndrome (PTS) is the most common complication of deep vein thrombosis (DVT) in children. OBJECTIVES: We aimed to assess the impact of pediatric PTS on functioning as assessed by movement ability, mobility, functional disability, and physical activity levels in children after diagnosis of limb DVT. METHODS: Patients aged 8-21 years in follow-up care after objectively documented limb DVT were prospectively recruited in this cross-sectional study. Measures of functioning (outcomes) included self-reported questionnaires that assessed: 1) movement ability, measured with the Movement Ability Measure-Computer Adaptive Test version; 2) mobility, evaluated with the Computer Adaptive Test version of the Patient-Reported Outcomes Measurement Information System Pediatric Physical Functioning, Mobility domain; 3) functional disability, evaluated with the Functional Disability Inventory; and 4) physical activity levels, evaluated with the Godin Leisure-Time Exercise Questionnaire. The main predictor was PTS severity, which was assessed using the index for the Clinical Assessment of PTS in children. The association between PTS and outcomes was analyzed using linear models. RESULTS: Eighty-seven patients (median age, 16 years; 25th-75th percentile, 15-18 years; 56% boys) were enrolled. Adjusted for age, sex, and underlying condition, increasing PTS severity was associated with lower current movement ability, a wider gap between current vs preferred movement ability, lower mobility, and slightly higher functional disability scores. There was a nonsignificant effect of PTS severity on moderate-strenuous physical activity. CONCLUSION: In children, increased PTS severity is associated with lower movement ability and impaired mobility. Reducing the gap between the patients' current vs preferred movement ability is a relevant aspect of PTS management in children.