Predicting Post-Operative Complications with Wearables

Abstract

Post-operative complications and hospital readmission are of great concern to surgical patients and health care providers. Wearable devices such as Fitbit wristbands enable long-term and non-intrusive monitoring of patients outside clinical environments. To build accurate predictive models based on wearable data, however, requires effective feature engineering to extract high-level features from time series data collected by the wearable sensors. This paper presents a pipeline for developing clinical predictive models based on wearable sensors. The core of the pipeline is a multi-level feature engineering framework for extracting high-level features from fine-grained time series data. The framework integrates a set of techniques tailored for noisy and incomplete wearable data collected in real-world clinical studies: (1) singular spectrum analysis for extracting high-level features from daily features over the course of the study; (2) a set of daily features that are resilient to missing data in wearable time series data; (3) a K-Nearest Neighbors (KNN) method for imputing short missing heart rate segments; (4) the integration of patients' clinical characteristics and wearable features. We evaluated the feature engineering approach and machine learning models in a clinical study involving 61 patients undergoing pancreatic surgery. Linear support vector machine (SVM) with integrated feature engineering achieved an AUROC of 0.8802 for predicting post-operative readmission or severe complications, which significantly outperformed the existing rule-based model used in clinical practice and other state-of-the-art feature engineering approaches.

Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data

“…We included predictors from EHR and wearable devices that might affect acute postoperative pain and chronic opioid use. [4][5][6][7][8][9][10] The variables were grouped into five domains: (1) demographics (e.g., age, gender, race, and ethnicity) and socioeconomic status (e.g., income, education);…”

“…Recent studies show that the use of Machine Learning (ML) models might predict pain and opioid requirements following surgery. [4][5][6][7][8][9][10] However, ML applications in acute pain management have been limited by population, surgery type, and the electronic health records (EHR) predictors used for model development. The present study explored the potential for ML models to predict postoperative acute pain and chronic opioid use.…”

“…The objective of this study was to explore the state-of-the-art application of ML techniques to predict acute postoperative pain and chronic opioid use. We: (1) developed a range of ML models; (2) compared model performance with others; [4][5][6][7][8][9][10] and (3) used advanced visualization technique (Shapley additive explanations (SHAP) 11 ) to identify the most pivotal predictors of model outcomes and individual patient outcomes.…”

Beyond Accuracy: A Critical Review of Fairness in Machine Learning for Mobile and Wearable Computing

“…UbiComp-based augmentation of human intelligence, such as cognitive load measurement [140], or cognitive performance prediction [140] may enable humans to do more, better, and faster (human agency). UbiComp-based innovations in medicine, such as PTSD screening [116], medication adherence monitoring [150], or post-operative complications prediction [152], may reinvent society by radically enhancing what humans are collectively capable of (individual and societal capabilities), while UbiComp-supported cooperative work, such as social context inference [89], may support societal cohesion and collaboration (societal cohesion).…”

“…However, pre-habilitation delays surgery and the patients might miss their opportunity for successful recovery and surgery is the only cure for the cancer." [152]. On the contrary, in speech-based human identification scenarios, false positive outcomes are critical in preventing unauthorized access, as "existing voiceprint-based authentication often suffers from various voice spoofing attacks" [40].…”