Towards streamlining orthopedic consultations: Machine learning classification of knee diagnosis groups via
Jacobien H F Oosterhoff1, Twan Slaats1, Tristan Warren2
1Faculty of Technology Policy and Management, Delft University of Technology, Delft, the Netherlands.
Background:
The number of patients suffering from knee complaints is increasing, leading to increased orthopedic healthcare consumption. Predicting knee diagnoses prior to consultation may be valuable in optimizing the consultation workflow. Therefore, the purpose of this study was to develop and internally validate a machine learning (ML) algorithm for predicting a knee diagnosis group for patients aged 18 years and older, based on computer-assisted history taking.
Methods:
A prospective cohort study at a single general district hospital was conducted to identify patients referred to an orthopedic surgeon for knee complaints. In total, 1172 patients were included, with an average age of 54 years (interquartile range 36-66), of which the majority were female (n = 594, 50.7%). The most frequent diagnosis group was knee osteoarthritis (n = 775, 66.1%), followed by ligamentous injuries (n = 208, 17.7%) and otherwise classified (n = 189, 16.1%). First, the dataset was randomly split 80:20 into training and test subsets. Then, a random forest algorithm was used to identify the variables predictive of a knee diagnosis group. Five different ML algorithms were developed, internally validated, and assessed by discrimination (area under the receiver operating characteristic curve, AUC), accuracy, precision (positive predictive value), recall (sensitivity), and F1‑score (the harmonic mean of precision and recall).
Results:
The models included patient characteristics and computer-assisted history taking. The support vector machine algorithm had the best performance for knee diagnosis group prediction, with good discrimination (area under the receiver operating characteristic curve, AUC = 0.92), accuracy (0.84), precision (0.85), recall (0.84) and F1-score (0.82).
Conclusions:
The developed ML algorithm shows promise in predicting a knee diagnosis group in patients presenting with knee complaints to an orthopedic practice. Integrating this algorithm could streamline the consultation workflow by directing patients predicted to have knee osteoarthritis to orthopedic surgeons specializing in knee osteoarthritis, and those predicted to have ligamentous injuries to orthopedic surgeons specializing in sports and traumatic injuries.
