DeepBackRib: Deep learning to understand factors associated with readmissions after rib fractures

Abstract

BACKGROUND:Deep neural networks yield high predictive performance, yet obscure interpretability limits clinical applicability. We aimed to build an explainable deep neural network that elucidates factors associated with readmissions after rib fractures among nonelderly adults, termed DeepBackRib. We hypothesized that DeepBackRib could accurately predict readmissions and a game theoretic approach to elucidate how predictions are made would facilitate model explainability. METHODS:We queried the 2017 National Readmissions Database for index hospitalization encounters of adults aged 18 to 64 years hospitalized with multiple rib fractures. The primary outcome was 3-month readmission(s). Study cohort was split 60-20-20 into trainingvalidation-test sets. Model input features included demographic/injury/index hospitalization characteristics and index hospitalization International Classification of Diseases, Tenth Revision, diagnosis codes. The seven-layer DeepBackRib comprised multipronged strategies to mitigate overfitting and was trained to optimize recall. Shapley additive explanation analysis identified the marginal contribution of each input feature for predicting readmissions. RESULTS:A total of 20,260 patients met the inclusion criteria, among whom 11% (n = 2,185) experienced 3-month readmissions. Feature selection narrowed 3,164 candidate input features to 61, and DeepBackRib yielded 91%, 85%, and 82% recall on the training, validation, and test sets, respectively. Shapley additive explanation analysis quantified the marginal contribution of each input feature in determining DeepBackRib's predictions: underlying chronic obstructive pulmonary disease and long index hospitalization length of stay had positive associations with 3-month readmissions, while private primary payer and diagnosis of pneumothorax during index admission had negative associations. CONCLUSION:We developed and internally validated a high-performing deep learning algorithm that elucidates factors associated with readmissions after rib fractures. Despite promising predictive performance, standalone deep learning algorithms are insufficient for clinical prediction tasks: a concerted effort is needed to ensure that clinical prediction algorithms remain explainable.

The Application of Design Thinking in Developing a Deep Learning Algorithm for Hip Fracture Detection

“…While physician experience is essential for providing high-quality clinical trauma care and treatment [ 19 , 20 ], information from various imaging modalities is also critical [ 21 , 22 , 23 ]. The goal of incorporating DL in trauma care is to hasten the diagnostic process, streamline therapeutic decision-making, and ultimately improve patient outcomes [ 24 , 25 ]. Therefore, it is crucial to develop an iterative DL algorithm that can be effectively implemented in clinical practice.…”

Expert consensus guidance on respiratory physiotherapy and rehabilitation of patients with rib fractures: An international, multidisciplinary e-Delphi study

“… 1 Difficulties in the management of patients with rib fractures are becoming increasingly well recognized in the literature. 2 , 3 There is limited research supporting optimal respiratory physiotherapy or physical rehabilitation strategies for patients with rib fractures, and as a result, no consensus exists for physiotherapists/physical therapists managing this patient group. A global survey study investigating current physiotherapy management of patients with chest trauma reported that, although mobilization activities as a treatment strategy is commonly used in the acute phase of the injury, other interventions are diverse, and their impact on patient outcomes needs further exploration.…”

“…Rib fractures account for more than 15% of all trauma admissions worldwide, with the most common injury mechanisms being low velocity falls, high velocity falls, road traffic collisions, assaults, and sporting injuries 1 . Difficulties in the management of patients with rib fractures are becoming increasingly well recognized in the literature 2,3 . There is limited research supporting optimal respiratory physiotherapy or physical rehabilitation strategies for patients with rib fractures, and as a result, no consensus exists for physiotherapists/physical therapists managing this patient group.…”

Clinical prediction models for the management of blunt chest trauma in the Emergency Department: a systematic review

“…4,5 These predictors include patient age, severity of injury, number and location of rib fractures, pre-injury anticoagulants, chronic lung disease and others. 4,[6][7][8] A common aim of such primary prognostic studies is the development of clinical prediction models. The clinical prediction model is intended to estimate the individualised probability or risk that a condition, for example mortality or pulmonary complications, will occur in the future by combining multiple prognostic factors / predictors from an individual.…”