Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Background: There are few safe effective ways to relieve osteoarthritis (OA) pain; as a result, off-label psychotropic drug prescriptions have increased worldwide. This study examined the change in psychotropic drug prescriptions for patients with OA from 2011 to 2020 using the Korean National Health Insurance Service dataset. Methods: The study population consisted of patients with hip or knee OA aged ≥ 65 years.Psychotropic drugs included opioids, benzodiazepines, non-benzodiazepine hypnotics (Z-drugs), anti-epileptics, tricyclic antidepressants, selective serotonin reuptake inhibitors (SSRIs), serotonin and norepinephrine reuptake inhibitors (SNRIs), typical antipsychotics, atypical antipsychotics, and anxiolytics. The prevalence and long-term (> 3 months) prescription rates of psychotropic drugs in OA patients were calculated. Results: The study included 1,821,158 patients with OA (mean age 71.7 years; 65.32% female).Of the cohort, 49% had comorbidities for which psychotropics were indicated. The prevalence of psychotropic prescriptions decreased from 58.2% to 52.0% in 2018 and then leveled off.The long-term prescription rate remained constant until 2018 and then increased slightly.The most commonly prescribed psychotropics were opioids and long- and short-acting benzodiazepines. The prescription rates of opioids and long-acting benzodiazepines decreased from 2011 to 2020. For those with psychiatric co-morbidities, the prescription rates of anti-epileptics and SNRIs increased, while the prescription rates of anti-epileptics, SSRIs, other antidepressants, and atypical psychotropics increased for those without such co-morbidities. The most commonly prescribed psychotropics were diazepam and alprazolam, excluding tramadol and tramadol–acetaminophen combination. For those with psychiatric co-morbidities, the prescription rates of gabapentin and fentanyl increased, while for those without such co-morbidities, the prescription rates of lorazepam, fentanyl, escitalopram and quetiapine increased. Conclusion A significant number of older Korean patients with OA were prescribed psychotropic drugs in the absence of comorbidities requiring such drugs, including drugs that have little effect on OA and unfavorable safety profiles in older adults.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Background: There are few safe effective ways to relieve osteoarthritis (OA) pain; as a result, off-label psychotropic drug prescriptions have increased worldwide. This study examined the change in psychotropic drug prescriptions for patients with OA from 2011 to 2020 using the Korean National Health Insurance Service dataset. Methods: The study population consisted of patients with hip or knee OA aged ≥ 65 years.Psychotropic drugs included opioids, benzodiazepines, non-benzodiazepine hypnotics (Z-drugs), anti-epileptics, tricyclic antidepressants, selective serotonin reuptake inhibitors (SSRIs), serotonin and norepinephrine reuptake inhibitors (SNRIs), typical antipsychotics, atypical antipsychotics, and anxiolytics. The prevalence and long-term (> 3 months) prescription rates of psychotropic drugs in OA patients were calculated. Results: The study included 1,821,158 patients with OA (mean age 71.7 years; 65.32% female).Of the cohort, 49% had comorbidities for which psychotropics were indicated. The prevalence of psychotropic prescriptions decreased from 58.2% to 52.0% in 2018 and then leveled off.The long-term prescription rate remained constant until 2018 and then increased slightly.The most commonly prescribed psychotropics were opioids and long- and short-acting benzodiazepines. The prescription rates of opioids and long-acting benzodiazepines decreased from 2011 to 2020. For those with psychiatric co-morbidities, the prescription rates of anti-epileptics and SNRIs increased, while the prescription rates of anti-epileptics, SSRIs, other antidepressants, and atypical psychotropics increased for those without such co-morbidities. The most commonly prescribed psychotropics were diazepam and alprazolam, excluding tramadol and tramadol–acetaminophen combination. For those with psychiatric co-morbidities, the prescription rates of gabapentin and fentanyl increased, while for those without such co-morbidities, the prescription rates of lorazepam, fentanyl, escitalopram and quetiapine increased. Conclusion A significant number of older Korean patients with OA were prescribed psychotropic drugs in the absence of comorbidities requiring such drugs, including drugs that have little effect on OA and unfavorable safety profiles in older adults.

Background: There are few safe effective ways to relieve osteoarthritis (OA) pain; as a result, off-label psychotropic drug prescriptions have increased worldwide. This study examined the change in psychotropic drug prescriptions for patients with OA from 2011 to 2020 using the Korean National Health Insurance Service dataset. Methods: The study population consisted of patients with hip or knee OA aged ≥ 65 years.Psychotropic drugs included opioids, benzodiazepines, non-benzodiazepine hypnotics (Z-drugs), anti-epileptics, tricyclic antidepressants, selective serotonin reuptake inhibitors (SSRIs), serotonin and norepinephrine reuptake inhibitors (SNRIs), typical antipsychotics, atypical antipsychotics, and anxiolytics. The prevalence and long-term (> 3 months) prescription rates of psychotropic drugs in OA patients were calculated. Results: The study included 1,821,158 patients with OA (mean age 71.7 years; 65.32% female).Of the cohort, 49% had comorbidities for which psychotropics were indicated. The prevalence of psychotropic prescriptions decreased from 58.2% to 52.0% in 2018 and then leveled off.The long-term prescription rate remained constant until 2018 and then increased slightly.The most commonly prescribed psychotropics were opioids and long- and short-acting benzodiazepines. The prescription rates of opioids and long-acting benzodiazepines decreased from 2011 to 2020. For those with psychiatric co-morbidities, the prescription rates of anti-epileptics and SNRIs increased, while the prescription rates of anti-epileptics, SSRIs, other antidepressants, and atypical psychotropics increased for those without such co-morbidities. The most commonly prescribed psychotropics were diazepam and alprazolam, excluding tramadol and tramadol–acetaminophen combination. For those with psychiatric co-morbidities, the prescription rates of gabapentin and fentanyl increased, while for those without such co-morbidities, the prescription rates of lorazepam, fentanyl, escitalopram and quetiapine increased. Conclusion A significant number of older Korean patients with OA were prescribed psychotropic drugs in the absence of comorbidities requiring such drugs, including drugs that have little effect on OA and unfavorable safety profiles in older adults.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Background: There are few safe effective ways to relieve osteoarthritis (OA) pain; as a result, off-label psychotropic drug prescriptions have increased worldwide. This study examined the change in psychotropic drug prescriptions for patients with OA from 2011 to 2020 using the Korean National Health Insurance Service dataset. Methods: The study population consisted of patients with hip or knee OA aged ≥ 65 years.Psychotropic drugs included opioids, benzodiazepines, non-benzodiazepine hypnotics (Z-drugs), anti-epileptics, tricyclic antidepressants, selective serotonin reuptake inhibitors (SSRIs), serotonin and norepinephrine reuptake inhibitors (SNRIs), typical antipsychotics, atypical antipsychotics, and anxiolytics. The prevalence and long-term (> 3 months) prescription rates of psychotropic drugs in OA patients were calculated. Results: The study included 1,821,158 patients with OA (mean age 71.7 years; 65.32% female).Of the cohort, 49% had comorbidities for which psychotropics were indicated. The prevalence of psychotropic prescriptions decreased from 58.2% to 52.0% in 2018 and then leveled off.The long-term prescription rate remained constant until 2018 and then increased slightly.The most commonly prescribed psychotropics were opioids and long- and short-acting benzodiazepines. The prescription rates of opioids and long-acting benzodiazepines decreased from 2011 to 2020. For those with psychiatric co-morbidities, the prescription rates of anti-epileptics and SNRIs increased, while the prescription rates of anti-epileptics, SSRIs, other antidepressants, and atypical psychotropics increased for those without such co-morbidities. The most commonly prescribed psychotropics were diazepam and alprazolam, excluding tramadol and tramadol–acetaminophen combination. For those with psychiatric co-morbidities, the prescription rates of gabapentin and fentanyl increased, while for those without such co-morbidities, the prescription rates of lorazepam, fentanyl, escitalopram and quetiapine increased. Conclusion A significant number of older Korean patients with OA were prescribed psychotropic drugs in the absence of comorbidities requiring such drugs, including drugs that have little effect on OA and unfavorable safety profiles in older adults.

Purpose: To develop a machine learning (ML) classifier for predicting post-induction hypotension (PIH) in non-cardiac surgeries. Materials and Methods: Preoperative data and early vital signs were obtained from 3669 cases in the VitalDB database, an opensource registry. PIH was defined as sustained mean arterial pressure (MAP) <65 mm Hg within 20 minutes since induction or from induction to incision. Six different ML algorithms were used to create binary classifiers to predict PIH. The primary outcome was the area under the receiver operating characteristic curve (AUROC) of ML classifiers. Results: A total of 2321 (63.3%) cases exhibited PIH. Among ML classifiers, the random forest regressor and extremely gradient boosting regressor showed the highest AUROC, both recording a value of 0.772. Excluding these models, the light gradient boosting machine regressor showed the second highest AUROC [0.769; 95% confidence interval (CI), 0.767–0.771], followed by the gradient boosting regressor (0.768; 95% CI, 0.763–0.772), AdaBoost regressor (0.752; 95% CI, 0.743–0.761), and automatic relevance determination regression (0.685; 95% CI, 0.669–0.701). The top three important features were mean diastolic blood pressure (DBP), minimum MAP, and minimum DBP from anesthetic induction to tracheal intubation, and these features were lower in cases with PIH (all p<0.001). Conclusion ML classifiers exhibited moderate performance in predicting PIH, and have the potential for real-time prediction.

Background: Few studies have evaluated the use of automated artificial intelligence (AI)-based pain recognition in postoperative settings or the correlation with pain intensity. In this study, various machine learning (ML)-based models using facial expressions, the analgesia nociception index (ANI), and vital signs were developed to predict postoperative pain intensity, and their performances for predicting severe postoperative pain were compared. Methods: In total, 155 facial expressions from patients who underwent gastrectomy were recorded postoperatively; one blinded anesthesiologist simultaneously recorded the ANI score, vital signs, and patient self-assessed pain intensity based on the 11-point numerical rating scale (NRS). The ML models’ area under the receiver operating characteristic curves (AUROCs) were calculated and compared using DeLong’s test. Results: ML models were constructed using facial expressions, ANI, vital signs, and different combinations of the three datasets. The ML model constructed using facial expressions best predicted an NRS ≥ 7 (AUROC 0.93) followed by the ML model combining facial expressions and vital signs (AUROC 0.84) in the test-set. ML models constructed using combined physiological signals (vital signs, ANI) performed better than models based on individual parameters for predicting NRS ≥ 7, although the AUROCs were inferior to those of the ML model based on facial expressions (all P < 0.050). Among these parameters, absolute and relative ANI had the worst AUROCs (0.69 and 0.68, respectively) for predicting NRS ≥ 7. Conclusions The ML model constructed using facial expressions best predicted severe postoperative pain (NRS ≥ 7) and outperformed models constructed from physiological signals.