Predicting inadequate postoperative pain management in depressed patients: A machine learning approach

• Published in: PloS one 2019-02, Vol.14 (2), p.e0210575-e0210575
• Main Authors: Parthipan, Arjun, Banerjee, Imon, Humphreys, Keith, Asch, Steven M, Curtin, Catherine, Carroll, Ian, Hernandez-Boussard, Tina
• Format: Article
• Language: English
• Subjects: Adult; Aged; Algorithms; Analgesics; Annotations; Antidepressants; Antidepressive Agents - administration & dosage; Care and treatment; Complications and side effects; Computer applications; Cytochrome P-450; Data mining; Demographic aspects; Demographics; Demography; Depression (Mood disorder); Depression - drug therapy; Discharge; Drug Prescriptions; Drug tolerance; Electronic Health Records; Female; Health care facilities; Hospital patients; Humans; Hydrocodone - administration & dosage; Information processing; Learning algorithms; Liver; Machine Learning; Male; Mathematical models; Medical centers; Medical schools; Medicine and Health Sciences; Mental depression; Methods; Middle Aged; Models, Biological; Morphine; Narcotics; Natural Language Processing; Opioids; Oxycodone; Pain; Pain management; Pain Management - methods; Pain, Postoperative - drug therapy; Pain, Postoperative - physiopathology; Patients; Phenols (Class of compounds); Postoperative pain; Postoperative Period; Predictions; Prescription writing; Psychotropic drugs; Selective serotonin reuptake inhibitors; Serotonin; Serotonin uptake inhibitors; Serotonin Uptake Inhibitors - administration & dosage; Signs and symptoms; Surgery; Test procedures; Unstructured data
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0210575

Widely-prescribed prodrug opioids (e.g., hydrocodone) require conversion by liver enzyme CYP-2D6 to exert their analgesic effects. The most commonly prescribed antidepressant, selective serotonin reuptake inhibitors (SSRIs), inhibits CYP-2D6 activity and therefore may reduce the effectiveness of prodrug opioids. We used a machine learning approach to identify patients prescribed a combination of SSRIs and prodrug opioids postoperatively and to examine the effect of this combination on postoperative pain control. Using EHR data from an academic medical center, we identified patients receiving surgery over a 9-year period. We developed and validated natural language processing (NLP) algorithms to extract depression-related information (diagnosis, SSRI use, symptoms) from structured and unstructured data elements. The primary outcome was the difference between preoperative pain score and postoperative pain at discharge, 3-week and 8-week time points. We developed computational models to predict the increase or decrease in the postoperative pain across the 3 time points by using the patient's EHR data (e.g. medications, vitals, demographics) captured before surgery. We evaluate the generalizability of the model using 10-fold cross-validation method where the holdout test method is repeated 10 times and mean area-under-the-curve (AUC) is considered as evaluation metrics for the prediction performance. We identified 4,306 surgical patients with symptoms of depression. A total of 14.1% were prescribed both an SSRI and a prodrug opioid, 29.4% were prescribed an SSRI and a non-prodrug opioid, 18.6% were prescribed a prodrug opioid but were not on SSRIs, and 37.5% were prescribed a non-prodrug opioid but were not on SSRIs. Our NLP algorithm identified depression with a F1 score of 0.95 against manual annotation of 300 randomly sampled clinical notes. On average, patients receiving prodrug opioids had lower average pain scores (p0.05). The machine learning algorithm accurately predicted the increase or decrease of the discharge, 3-week and 8-week follow-up pain scores when compared to the pre-operative pain score using 10-fold cross validation (mean ar