ABSTRACT
Introduction: Opioid use disorder is a cause for concern globally. This study aimed to optimize methadone dose adjustments using mixed modeling and machine learning. Methods: This retrospective study was conducted at Taichung Veterans General Hospital between January 1, 2019, and December 31, 2020. Overall, 40,530 daily dosing records and 1,508 urine opiate test results were collected from 96 patients with opioid use disorder. A two-stage approach was used to create a model of the optimized methadone dose. In Stage 1, mixed modeling was performed to analyze the association between methadone dose, age, sex, treatment duration, HIV positivity, referral source, urine opiate level, last methadone dose taken, treatment adherence, and likelihood of treatment discontinuation. In Stage 2, machine learning was performed to build a model for optimized methadone dose. Results: Likelihood of discontinuation was associated with reduced methadone doses (ß = 0.002, 95% CI = 0.000-0.081). Correlation analysis between the methadone dose determined by physicians and the optimized methadone dose showed a mean correlation coefficient of 0.995 ± 0.003, indicating that the difference between the methadone dose determined by physicians and that determined by the model was within the allowable range (p < 0.001). Conclusion: We developed a model for methadone dose adjustment in patients with opioid use disorders. By integrating urine opiate levels, treatment adherence, and likelihood of treatment discontinuation, the model could suggest automatic adjustment of the methadone dose, particularly when face-to-face encounters are impractical.
ABSTRACT
BACKGROUND: Sleepiness-at-the-wheel has been identified as a major cause of highway accidents. The aim of our study is identifying the candidate measures for home-based screening of sleep disordered breathing in Taiwanese bus drivers, instead of polysomnography. METHODS: Overnight polysomnography accompanied with simultaneous measurements of alternative screening devices (pulse oximetry, ApneaLink, and Actigraphy), heart rate variability, wake-up systolic blood pressure and questionnaires were completed by 151 eligible participants who were long-haul bus drivers with a duty period of more than 12 h a day and duty shifting. RESULTS: 63.6% of professional bus drivers were diagnosed as having sleep disordered breathing and had a higher body mass index, neck circumference, systolic blood pressure, arousal index and desaturation index than those professional bus drivers without evidence of sleep disordered breathing. Simple home-based candidate measures: (1) Pulse oximetry, oxygen-desaturation indices by ≥3% and 4% (r = 0.87~0.92); (2) Pulse oximetry, pulse-rising indices by ≥7% and 8% from a baseline (r = 0.61~0.89); and (3) ApneaLink airflow detection, apnea-hypopnea indices (r = 0.70~0.70), based on recording-time or Actigraphy-corrected total sleep time were all significantly correlated with, and had high agreement with, corresponding polysomnographic apnea-hypopnea indices [(1) 94.5%~96.6%, (2) 93.8%~97.2%, (3) 91.1%~91.3%, respectively]. Conversely, no validities of SDB screening were found in the multi-variables apnea prediction questionnaire, Epworth Sleepiness Scale, night-sleep heart rate variability, wake-up systolic blood pressure and anthropometric variables. CONCLUSIONS: The indices of pulse oximetry and apnea flow detection are eligible criteria for home-based screening of sleep disordered breathing, specifically for professional drivers.