Naïve Bayes is an interpretable and predictive machine learning algorithm in predicting osteoporotic hip fracture in-hospital mortality compared to other machine learning algorithms

Osteoporotic hip fractures (HFs) in the elderly are a pertinent issue in healthcare, particularly in developed countries such as Australia. Estimating prognosis following admission remains a key challenge. Current predictive tools require numerous patient input features including those unavailable early in admission. Moreover, attempts to explain machine learning [ML]-based predictions are lacking. Seven ML prognostication models were developed to predict in-hospital mortality following minimal trauma HF in those aged ≥ 65 years of age, requiring only sociodemographic and comorbidity data as input. Hyperparameter tuning was performed via fractional factorial design of experiments combined with grid search; models were evaluated with 5-fold cross-validation and area under the receiver operating characteristic curve (AUROC). For explainability, ML models were directly interpreted as well as analysed with SHAP values. Top performing models were random forests, naïve Bayes [NB], extreme gradient boosting, and logistic regression (AUROCs ranging 0.682–0.696, p>0.05). Interpretation of models found the most important features were chronic kidney disease, cardiovascular comorbidities and markers of bone metabolism; NB also offers direct intuitive interpretation. Overall, NB has much potential as an algorithm, due to its simplicity and interpretability whilst maintaining competitive predictive performance.Author summary: Osteoporotic hip fractures are a critical health issue in developed countries. Preventative measures have ameliorated this issue somewhat, but the problem is expected to remain in main due to the aging population. Moreover, the mortality rate of patients in-hospital remains unacceptably high, with estimates ranging from 5–10%. Thus, a risk stratification tool would play a critical role in optimizing care by facilitating the identification of the susceptible elderly in the community for prevention measures and the prioritisation of such patients early during their hospital admission. Unfortunately, such a tool has thus far remained elusive, despite forays into relatively exotic algorithms in machine learning. There are three major drawbacks (1) most tools all rely on information typically unavailable in the community and early during admission (for example, intra-operative data), limiting their potential use in practice, (2) few studies compare their trained models with other potential algorithms and (3) machine learning models are commonly cited as being ‘black boxes’ and uninterpretable. Here it is shown that a Naïve Bayes model, trained using only sociodemographic and comorbidity data of patients, performs on par with the more popular methods lauded in literature. The model is interpretable through direct analysis; the comorbidities of chronic kidney disease, cardiovascular, and bone metabolism were identified as being important features contributing to the likelihood of deaths. An algorithm-agnostic approach to machine learning model interpretation is also shown. This study shows the potential for Naïve Bayes in predicting elderly patients at risk of death during an admission for hip fracture.