Machine Learning Model to Predict Allocation of Patients with Chronic Back Pain for Integrated Practice Units in a System of Value-based Health Care

Chronic pain incurs substantial global healthcare costs, requiring long-term specialized care. However, the variability in treatment approaches hampers the feasibility of value-based healthcare. To advance management and prevention efforts, data science tools like supervised and unsupervised machine learning algorithms offer promising solutions. This study employed data from six questionnaires to evaluate pain conditions in patients. Correlation techniques were applied to determine the questions most strongly correlated with low back pain, back pain, and leg pain. Five machine learning algorithms predicted the presence or absence of pain in the low back region. Seven variables were identified as input for the prediction models, with the XBoost Classifier demonstrating the highest accuracy, precision, recall, and F1-Score (0.8 accuracy, precision, recall; 0.78 F1-Score). By incorporating the machine learning model, it predicts the allocation of chronic back pain patients to integrated practice in a value-based healthcare system. Finally, our findings show that data science methods, such as machine learning, improve chronic pain management, expedite surveys, and improve value-based healthcare through efficient allocation. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=90 SRC="FIGDIR/small/23298111v1_ufig1.gif" ALT="Figure 1"> View larger version (32K): org.highwire.dtl.DTLVardef@1b7b12eorg.highwire.dtl.DTLVardef@d18170org.highwire.dtl.DTLVardef@88e59corg.highwire.dtl.DTLVardef@19a85dd_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LICorrelation analysis identified pain-related questions (back, leg, chronic low back). C_LIO_LI7 characteristics used by ML algorithms to forecast chronic low back pain occurrence. C_LIO_LIXBoost algorithm and neural network achieved best performance (Precision, Recall [~]0.8). C_LIO_LIOutcomes aid patient allocation, screening, and reducing costs in value-based healthcare. C_LIO_LIStreamlining surveys boosts response rates and enables larger datasets for improved modeling. C_LI