Shusuke Numata

Background/Objectives: Automatically estimated affective states are increasingly used to monitor mental health, yet such indices are rarely validated against expert clinical judgement of the same recordings. When an automated index fails to match self-report, the source of the failure is ambiguous: the recordings may not contain the relevant signal, or the model may fail to recover a signal that is present. This exploratory study introduced an independent observer standard to separate these possibilities, and examined how expert ratings, brief personality measures and a multimodally estimated stress index each relate to day-to-day self-reported depressive symptoms in school employees without psychiatric diagnosis or treatment contact. Methods: School employees completed daily assessments comprising a fixed three-turn recorded dialogue with a conversational agent followed by the nine-item Patient Health Questionnaire (PHQ-9). Ten participants with baseline trait data and at least four person-days (153 person-days, median 10.5, range 4–44) formed the primary sample; autistic traits (Autism-Spectrum Quotient, AQ) and personality (Japanese Ten Item Personality Inventory, TIPI-J) were measured once at baseline. Three clinicians independently rated 47 recorded sessions from seven participants on Item 1 (Apparent Sadness) of the Montgomery–Åsberg Depression Rating Scale across facial, acoustic, linguistic and overall channels, yielding 41 person-days with a concurrent PHQ-9 and a valid automated index. The index was produced by LightGBM classifiers over speech, facial and linguistic features, trained on binarised PHQ-9/GAD-7 labels from counselling interviews. Associations were tested with permutation-based Spearman correlations, linear mixed models with within-participant permutation tests and cluster bootstrap intervals, and area under the curve (AUC), with false discovery rate (FDR) correction. Results: In the ten-participant trait sample, neuroticism correlated with mean PHQ-9 (ρ = 0.90, q = 0.019) and agreeableness inversely (ρ = −0.84, q = 0.027); both associations persisted when any one participant was omitted. Associations with symptom variability did not survive adjustment for symptom level, to which variability was tightly coupled (ρ = 0.92). In the seven-participant validation subsample, expert ratings of spoken content were associated with same-day PHQ-9 (b = 3.13, cluster bootstrap 95% CI 1.46 to 3.48, permutation p = 0.013) and the association withstood tests for serial dependence, but it was sensitive to which clinicians’ ratings were included, and averaged ratings reached only moderate reliability (ICC(2,3) 0.49–0.56); facial, vocal and overall ratings were not significantly associated. The automated index showed no association with expert ratings after FDR correction (smallest q = 0.22), showed no demonstrable association with concurrent PHQ-9 (withinperson r = 0.08, 95% CI −0.14 to 0.31) and did not discriminate PHQ-9 ≥ 5 above chance (AUC 0.59, 95% CI 0.44–0.77). Only 13.2% of its variance lay between participants, versus 81.3% for PHQ-9. Conclusions: In this small sample, brief personality measures tracked the level of self-reported depressive symptoms, and expert ratings of spoken content were associated with daily symptoms, although the latter association depended on which clinicians’ ratings were included; concurrent validity of the automated index was not demonstrated against either standard. Inspection of the deployed pipeline indicated output saturation arising from a high-sensitivity operating point. Classifier outputs optimised for case detection should not be repurposed as graded severity indices without recalibration. These hypothesis-generating findings require replication in adequately powered samples.

Depression is a serious social issue, and early detection is crucial for improving mental health care. This study constructed a Japanese multimodal dataset for early depression detection, collecting text, audio, video, and heart rate data from 30-minute interviews with professional counselors. Psychological questionnaires were also administered before and after interviews. Feature extraction and correlation analysis with questionnaire results confirmed the dataset's reliability, aligning with existing psychological research. The dataset was then used to train DepMamba, a latest depression detection model, comparing three training methods. Fine-tuning the constructed dataset after pre-training on DAIC-WOZ significantly improved recall, enhancing depression detection performance. However, data limitations and label imbalances highlight the need for future dataset expansion and objective annotation. This research advances depression detection technology and supports the practical application of mental health care.

Recently, the use of digital technologies, such as avatars and virtual reality, has been increasingly explored to address university students’ mental health issues. However, there is limited research on the advantages and disadvantages of counselors using avatars in online video counseling. Herein, 25 university students were enrolled in a pilot online counseling session with a human counselor-controlled avatar, and asked about their emotional experiences and impressions of the avatar and to provide qualitative feedback on their communication experience. Positive emotions during the session were associated with impressions of the avatar’s intelligence and likeability. The anthropomorphism, animacy, likeability, and intelligent impressions of the avatar were interrelated, indicating that the avatar’s smile and the counselor’s expertise in empathy and approval may have contributed to these impressions. However, no associations were observed between participant experiences and their prior communication with avatars, or between participant experiences and their gender or the perceived gender of the avatar. Accordingly, recommendations for future practice and research are provided. Accumulating practical and empirical findings on the effectiveness of human-operated avatar counselors is crucial for addressing university students’ mental health issues.

Schizophrenia is a psychiatric disorder with cognitive dysfunction as a core symptom along with positive and negative symptoms. Cognitive dysfunction in schizophrenia can be broadly classified into neurocognitive and social cognitive deficits, with these deficits significantly influencing social functioning. Therapeutic interventions aiming to enhance neurocognition and social cognition have been developed. In this review, we describe the characteristics of cognitive dysfunction in patients with schizophrenia, its relationship to social function, and intervention strategies. J. Med. Invest. 71 : 205-209, August, 2024

Genomic DNA methylation is involved in many diseases and is expected to be a specific biomarker for even the pre-symptomatic diagnosis of many diseases. Thus, a rapid and inexpensive detection method is required for disease diagnosis. We have previously reported that cytosine methylation in G-quadruplex (G4)-forming oligonucleotides develops different G4 topologies. In this study, we developed a method for detecting CpG methylation in G4-forming oligonucleotides based on the structural differences between methylated and unmethylated G4 DNAs. The differences in G4 topologies due to CpG methylation can be discriminated by G4 ligands. We performed a binding assay between methylated or unmethylated G4 DNAs and G4 ligands. The binding abilities of fluorescent G4 ligands to BCL-2, HRAS1, HRAS2, VEGF G4-forming sequences were examined by fluorescence-based microtiter plate assay. The differences in fluorescence intensities between methylated and unmethylated G4 DNAs were statistically significant. In addition to fluorescence detection, the binding of G4 ligand to DNA was detected by chemiluminescence. A significant difference was also detected in chemiluminescence intensity between methylated and unmethylated DNA. This is the first study on the detection of CpG methylation in G4 structures, focusing on structural changes using G4 ligands.

Schizophrenia is a mental illness that involves both genetic and environmental factors. Clozapine, an atypical antipsychotic, is a well-established therapy for treatment-resistant schizophrenia. In this study, we focused on a set of monozygotic twins with treatment-resistant schizophrenia in which one twin effectively responded to clozapine treatment and the other did not. Our previous study generated neurons from induced pluripotent stem (iPS) cells derived from these patients and compared the transcriptome profiles between mock- and clozapine-treated neurons. In this study, we performed genome-wide DNA methylation profiling to investigate the mechanisms underlying gene expression changes. First, we extracted the differentially methylated sites from each twin based on statistical analysis. Then, we combined the DNA methylation profiling with transcriptome profiling from our previous RNA-seq data. Among the genes with altered methylation and expression, we found the different proportions of the genes related to neuronal and synaptic functions between the clozapine responder and non-responder (35.7 and 6.7%, respectively). This trend was observed even when the basal differences between the responder and non-responder was excluded. These results suggest that effective clozapine action may correct the abnormalities of neuronal and synapse functions in schizophrenia via changes in methylation.