Discrimination between healthy participants and people with panic disorder based on polygenic scores for psychiatric disorders and for intermediate phenotypes using machine learning.

OBJECTIVE: Panic disorder is a modestly heritable condition. Currently, diagnosis is based only on clinical symptoms; identifying objective biomarkers and a more reliable diagnostic procedure is desirable. We investigated whether people with panic disorder can be reliably diagnosed utilizing combinations of multiple polygenic scores for psychiatric disorders and their intermediate phenotypes, compared with single polygenic score approaches, by applying specific machine learning techniques. METHODS: Polygenic scores for 48 psychiatric disorders and intermediate phenotypes based on large-scale genome-wide association studies (n = 7556-1,131,881) were calculated for people with panic disorder (n = 718) and healthy controls (n = 1717). Discrimination between people with panic disorder and healthy controls was based on the 48 polygenic scores using five methods for classification: logistic regression, neural networks, quadratic discriminant analysis, random forests and a support vector machine. Differences in discrimination accuracy (area under the curve) due to an increased number of polygenic score combinations and differences in the accuracy across five classifiers were investigated. RESULTS: All five classifiers performed relatively well for distinguishing people with panic disorder from healthy controls by increasing the number of polygenic scores. Of the 48 polygenic scores, the polygenic score for anxiety UK Biobank was the most useful for discrimination by the classifiers. In combinations of two or three polygenic scores, the polygenic score for anxiety UK Biobank was included as one of polygenic scores in all classifiers. When all 48 polygenic scores were used in combination, the greatest areas under the curve significantly differed among the five classifiers. Support vector machine and logistic regression had higher accuracy than quadratic discriminant analysis and random forests. For each classifier, the greatest area under the curve was 0.600 ± 0.030 for logistic regression (polygenic score combinations N = 14), 0.591 ± 0.039 for neural networks (N = 9), 0.603 ± 0.033 for quadratic discriminant analysis (N = 10), 0.572 ± 0.039 for random forests (N = 25) and 0.617 ± 0.041 for support vector machine (N = 11). The greatest areas under the curve at the best polygenic score combination significantly differed among the five classifiers. Random forests had the lowest accuracy among classifiers. Support vector machine had higher accuracy than neural networks. CONCLUSIONS: These findings suggest that increasing the number of polygenic score combinations up to approximately 10 effectively improved the discrimination accuracy and that support vector machine exhibited greater accuracy among classifiers. However, the discrimination accuracy for panic disorder, when based solely on polygenic score combinations, was found to be modest.

Live two-way video versus face-to-face treatment for depression, anxiety, and obsessive-compulsive disorder: A 24-week randomized controlled trial.

AIM: Live two-way video, easily accessible from home via smartphones and other devices, is becoming a new way of providing psychiatric treatment. However, lack of evidence for real-world clinical setting effectiveness hampers its approval by medical insurance in some countries. Here, we conducted the first large-scale pragmatic, randomized controlled trial to determine the effectiveness of long-term treatment for multiple psychiatric disorders via two-way video using smartphones and other devices, which are currently the primary means of telecommunication. METHODS: This randomized controlled trial compared two-way video versus face-to-face treatment for depressive disorder, anxiety disorder, and obsessive-compulsive disorder in the subacute/maintenance phase during a 24-week period. Adult patients with the above-mentioned disorders were allocated to either a two-way video group (≥50% video sessions) or a face-to-face group (100% in-person sessions) and received standard treatment covered by public medical insurance. The primary outcome was the 36-Item Short-Form Health Survey Mental Component Summary (SF-36 MCS) score. Secondary outcomes included all-cause discontinuation, working alliance, adverse events, and the severity rating scales for each disorder. RESULTS: A total of 199 patients participated in this study. After 24 weeks of treatment, two-way video treatment was found to be noninferior to face-to-face treatment regarding SF-36 MCS score (48.50 vs 46.68, respectively; p < 0.001). There were no significant differences between the groups regarding most secondary end points, including all-cause discontinuation, treatment efficacy, and satisfaction. CONCLUSION: Two-way video treatment using smartphones and other devices, was noninferior to face-to-face treatment in real-world clinical settings. Modern telemedicine, easily accessible from home, can be used as a form of health care.

The Association Between Physical Activity/Heart Rate Variability Data Obtained Using a Wearable Device and Timed Motor Functional Tests in Patients with Duchenne Muscular Dystrophy: A Pilot Study.

Background: Duchenne muscular dystrophy (DMD) is a devastating X-linked muscle disease. Clinical evaluation of DMD uses patient-intensive motor function tests, and the recent development of wearable devices allows the collection of a variety of biometric information, including physical activity. Objective: In this study, we examined differences in physical activity and heart rate variability (HRV) between patients with DMD and healthy subjects using a wearable device, and investigated any association between these parameters and motor function in patients with DMD. Methods: Participants were 7 patients with DMD and 8 healthy males, whose physical activity and HRV were provided by a wearable device. These data were used to investigate the relationship between both physical activity and HRV parameters and timed motor functional tests [Time to stand from supine, 10-meter walking time (10MWT), North Star Ambulatory Assessment (NSAA), and 6-minute walking test (6MWT)] in patients with DMD. Results: Results of 24-hours physical activity, fat burning, total number of steps and active distance, average step rate, average exercise intensity during walking, exercise, degree of forward lean during walking, maximum heart rate, normalized low frequency power (LF norm), and maximum exercise intensity in patients with DMD were lower than those in control subjects. Physical activity and HRV parameters did not correlate with the time to stand from supine. The 10MWT positively correlated with average heart rate, while NSAA negatively correlated with average heart rate, total frequency power (TF), and very low frequency power (VLF) during arousal. The 6MWT negatively correlated with ratio LF/high frequency power (HF). CONCLUSIONS: Physical activity and HRV indices that differ from those of normal children and that correlate with motor function assessment may serve as digital biomarkers.