Objective: Extrapyramidal symptoms (EPS) are common side effects of antipsychotic drugs. Despite the growing interest in exploring objective biomarkers for EPS prevention and the potential use of voice in detecting clinical disorders, no studies have demonstrated the relationships between vocal changes and EPS. Therefore, we aimed to determine the associations between voice changes and antipsychotic dosage, and further investigated whether speech characteristics could be used as predictors of EPS. Methods: Forty-two patients receiving or expected to receive antipsychotic drugs were recruited. Drug-induced parkinsonism of EPS was evaluated using the Simpson-Angus Scale (SAS). Participants’ voice data consisted of 16 neutral sentences and 2 second-long /Ah/utterances. Thirteen voice features were extracted from the obtained voice data. Each voice feature was compared between groups categorized based on SAS total score of below and above “0.6.” The associations between antipsychotic dosage and voice characteristics were examined, and vocal trait variations according to the presence of EPS were explored. Results: Significant associations were observed between specific vocal characteristics and antipsychotic dosage across both datasets of 1–16 sentences and /Ah/utterances. Notably, Mel-Frequency Cepstral Coefficients (MFCC) exhibited noteworthy variations in response to the presence of EPS. Specifically, among the 13 MFCC coefficients, MFCC1 (t=-4.47, p<0.001), MFCC8 (t=-4.49, p<0.001), and MFCC12 (t=-2.21, p=0.029) showed significant group differences in the overall statistical values. Conclusion Our results suggest that MFCC may serve as a predictor of detecting drug-induced parkinsonism of EPS. Further research should address potential confounding factors impacting the relationship between MFCC and antipsychotic dosage, possibly improving EPS detection and reducing antipsychotic medication side effects.

Objective: Extrapyramidal symptoms (EPS) are common side effects of antipsychotic drugs. Despite the growing interest in exploring objective biomarkers for EPS prevention and the potential use of voice in detecting clinical disorders, no studies have demonstrated the relationships between vocal changes and EPS. Therefore, we aimed to determine the associations between voice changes and antipsychotic dosage, and further investigated whether speech characteristics could be used as predictors of EPS. Methods: Forty-two patients receiving or expected to receive antipsychotic drugs were recruited. Drug-induced parkinsonism of EPS was evaluated using the Simpson-Angus Scale (SAS). Participants’ voice data consisted of 16 neutral sentences and 2 second-long /Ah/utterances. Thirteen voice features were extracted from the obtained voice data. Each voice feature was compared between groups categorized based on SAS total score of below and above “0.6.” The associations between antipsychotic dosage and voice characteristics were examined, and vocal trait variations according to the presence of EPS were explored. Results: Significant associations were observed between specific vocal characteristics and antipsychotic dosage across both datasets of 1–16 sentences and /Ah/utterances. Notably, Mel-Frequency Cepstral Coefficients (MFCC) exhibited noteworthy variations in response to the presence of EPS. Specifically, among the 13 MFCC coefficients, MFCC1 (t=-4.47, p<0.001), MFCC8 (t=-4.49, p<0.001), and MFCC12 (t=-2.21, p=0.029) showed significant group differences in the overall statistical values. Conclusion Our results suggest that MFCC may serve as a predictor of detecting drug-induced parkinsonism of EPS. Further research should address potential confounding factors impacting the relationship between MFCC and antipsychotic dosage, possibly improving EPS detection and reducing antipsychotic medication side effects.

Objective: Extrapyramidal symptoms (EPS) are common side effects of antipsychotic drugs. Despite the growing interest in exploring objective biomarkers for EPS prevention and the potential use of voice in detecting clinical disorders, no studies have demonstrated the relationships between vocal changes and EPS. Therefore, we aimed to determine the associations between voice changes and antipsychotic dosage, and further investigated whether speech characteristics could be used as predictors of EPS. Methods: Forty-two patients receiving or expected to receive antipsychotic drugs were recruited. Drug-induced parkinsonism of EPS was evaluated using the Simpson-Angus Scale (SAS). Participants’ voice data consisted of 16 neutral sentences and 2 second-long /Ah/utterances. Thirteen voice features were extracted from the obtained voice data. Each voice feature was compared between groups categorized based on SAS total score of below and above “0.6.” The associations between antipsychotic dosage and voice characteristics were examined, and vocal trait variations according to the presence of EPS were explored. Results: Significant associations were observed between specific vocal characteristics and antipsychotic dosage across both datasets of 1–16 sentences and /Ah/utterances. Notably, Mel-Frequency Cepstral Coefficients (MFCC) exhibited noteworthy variations in response to the presence of EPS. Specifically, among the 13 MFCC coefficients, MFCC1 (t=-4.47, p<0.001), MFCC8 (t=-4.49, p<0.001), and MFCC12 (t=-2.21, p=0.029) showed significant group differences in the overall statistical values. Conclusion Our results suggest that MFCC may serve as a predictor of detecting drug-induced parkinsonism of EPS. Further research should address potential confounding factors impacting the relationship between MFCC and antipsychotic dosage, possibly improving EPS detection and reducing antipsychotic medication side effects.

Objective: Extrapyramidal symptoms (EPS) are common side effects of antipsychotic drugs. Despite the growing interest in exploring objective biomarkers for EPS prevention and the potential use of voice in detecting clinical disorders, no studies have demonstrated the relationships between vocal changes and EPS. Therefore, we aimed to determine the associations between voice changes and antipsychotic dosage, and further investigated whether speech characteristics could be used as predictors of EPS. Methods: Forty-two patients receiving or expected to receive antipsychotic drugs were recruited. Drug-induced parkinsonism of EPS was evaluated using the Simpson-Angus Scale (SAS). Participants’ voice data consisted of 16 neutral sentences and 2 second-long /Ah/utterances. Thirteen voice features were extracted from the obtained voice data. Each voice feature was compared between groups categorized based on SAS total score of below and above “0.6.” The associations between antipsychotic dosage and voice characteristics were examined, and vocal trait variations according to the presence of EPS were explored. Results: Significant associations were observed between specific vocal characteristics and antipsychotic dosage across both datasets of 1–16 sentences and /Ah/utterances. Notably, Mel-Frequency Cepstral Coefficients (MFCC) exhibited noteworthy variations in response to the presence of EPS. Specifically, among the 13 MFCC coefficients, MFCC1 (t=-4.47, p<0.001), MFCC8 (t=-4.49, p<0.001), and MFCC12 (t=-2.21, p=0.029) showed significant group differences in the overall statistical values. Conclusion Our results suggest that MFCC may serve as a predictor of detecting drug-induced parkinsonism of EPS. Further research should address potential confounding factors impacting the relationship between MFCC and antipsychotic dosage, possibly improving EPS detection and reducing antipsychotic medication side effects.

OBJECTIVES: To develop a simple algorithm for prescreening of obstructive sleep apnea (OSA) on the basis of respiratorysounds recorded during polysomnography during all sleep stages between sleep onset and offset. METHODS: Patients who underwent attended, in-laboratory, full-night polysomnography were included. For all patients, audiorecordings were performed with an air-conduction microphone during polysomnography. Analyses included allsleep stages (i.e., N1, N2, N3, rapid eye movement, and waking). After noise reduction preprocessing, data were segmentedinto 5-s windows and sound features were extracted. Prediction models were established and validated with10-fold cross-validation by using simple logistic regression. Binary classifications were separately conducted for threedifferent threshold criteria at apnea hypopnea index (AHI) of 5, 15, or 30. Prediction model characteristics, includingaccuracy, sensitivity, specificity, positive predictive value (precision), negative predictive value, and area under thecurve (AUC) of the receiver operating characteristic were computed. RESULTS: A total of 116 subjects were included; their mean age, body mass index, and AHI were 50.4 years, 25.5 kg/m2, and23.0/hr, respectively. A total of 508 sound features were extracted from respiratory sounds recorded throughoutsleep. Accuracies of binary classifiers at AHIs of 5, 15, and 30 were 82.7%, 84.4%, and 85.3%, respectively. Predictionperformances for the classifiers at AHIs of 5, 15, and 30 were AUC, 0.83, 0.901, and 0.91; sensitivity, 87.5%,81.6%, and 60%; and specificity, 67.8%, 87.5%, and 94.1%. Respective precision values of the classifiers were89.5%, 87.5%, and 78.2% for AHIs of 5, 15, and 30. CONCLUSION: This study showed that our binary classifier predicted patients with AHI of ≥15 with sensitivity and specificityof >80% by using respiratory sounds during sleep. Since our prediction model included all sleep stage data, algorithmsbased on respiratory sounds may have a high value for prescreening OSA with mobile devices.
Apnea ; Area Under Curve ; Body Mass Index ; Classification ; Humans ; Logistic Models ; Machine Learning ; Noise ; Polysomnography ; Respiratory Sounds ; ROC Curve ; Sensitivity and Specificity ; Sleep Apnea, Obstructive ; Sleep Stages ; Sleep, REM