Multimodal digital assessment of depression with actigraphy and app in Hong Kong Chinese.

There is an emerging potential for digital assessment of depression. In this study, Chinese patients with major depressive disorder (MDD) and controls underwent a week of multimodal measurement including actigraphy and app-based measures (D-MOMO) to record rest-activity, facial expression, voice, and mood states. Seven machine-learning models (Random Forest [RF], Logistic regression [LR], Support vector machine [SVM], K-Nearest Neighbors [KNN], Decision tree [DT], Naive Bayes [NB], and Artificial Neural Networks [ANN]) with leave-one-out cross-validation were applied to detect lifetime diagnosis of MDD and non-remission status. Eighty MDD subjects and 76 age- and sex-matched controls completed the actigraphy, while 61 MDD subjects and 47 controls completed the app-based assessment. MDD subjects had lower mobile time (P = 0.006), later sleep midpoint (P = 0.047) and Acrophase (P = 0.024) than controls. For app measurement, MDD subjects had more frequent brow lowering (P = 0.023), less lip corner pulling (P = 0.007), higher pause variability (P = 0.046), more frequent self-reference (P = 0.024) and negative emotion words (P = 0.002), lower articulation rate (P < 0.001) and happiness level (P < 0.001) than controls. With the fusion of all digital modalities, the predictive performance (F1-score) of ANN for a lifetime diagnosis of MDD was 0.81 and 0.70 for non-remission status when combined with the HADS-D item score, respectively. Multimodal digital measurement is a feasible diagnostic tool for depression in Chinese. A combination of multimodal measurement and machine-learning approach has enhanced the performance of digital markers in phenotyping and diagnosis of MDD.

Non-invasive assessment of liver fibrosis with transient elastography (FibroScan®): applying the cut-offs of M probe to XL probe.

UNLABELLED: BACKGROUND AND RATIONALE FOR THE STUDY: Limited studies have aimed to define the cut-offs of XL probe (XL cut-offs) for different stages of liver fibrosis, whereas those of M probe (M cut-offs) may not be applicable to XL probe. We aimed to derive appropriate XL cut-offs in overweight patients. Patients with liver stiffness measurement (LSM) by both probes were recruited. XL cut-offs probe for corresponding M cut-offs were derived from an exploratory cohort, and subsequently validated in a subgroup patients also underwent liver biopsy. The diagnostic accuracy of XL cut-offs to diagnose advanced fibrosis was evaluated. RESULTS: Total 517 patients (63% male, mean age 58) who had reliable LSM by both probes were included in the exploratory cohort. There was a strong correlation between the LSM by M probe (LSM-M) and LSM by XL probe (LSM-XL) (r² = 0.89, p < 0.001). A decision tree using LSM-XL was learnt to predict the 3 categories of LSM-M (< 6.0kPa, 6.0-11.9kPa and ≥ 12.0kPa), and XL cut-offs at 4.8kPa and 10.7kPa were identified. These cut-offs were subsequently validated in a cohort of 147 patients who underwent liver biopsy. The overall accuracy was 89% among 62 patients whose LSM-XL < 4.8kPa or ≥ 10.7kPa. These cut-offs would have avoided under-staging of fibrosis among patients with body mass index (BMI) > 25-30 kg/m2 but not > 30 kg/m2. CONCLUSIONS: XL cut-offs at 4.8kPa and 10.7kPa were the best estimates of 6.0kPa and 12.0kPa of M probe for patients with BMI > 25-30 kg/m2. Patients with BMI > 30 kg/m² might use M probe cut-offs for XL probe.