Protocol for an ABT study: the role of emotional processing in Art Brut therapy for college students during the COVID-19 pandemic (preprint)

Background COVID-19 is both a global health emergency and a major psychological crisis event, and its negative effects on college students' mental health continue to persist after more than three years. Previous studies[1, 2] suggest that the overall psychological health status of students in colleges has been poor during the COVID-19 pandemic, especially among those vulnerable to emotional problems. Interventions are needed to improve the psychological health of college students. This study was designed to determine the potential role of art brut therapy as a positive psychological health approach for university students. Methods A sample of university students (n = 120) will be recruited and assigned to an Offline Art Brut Group (OFABG), Online Art Brut Group (OABG), or a control group (CG) with no intervention. Prior to inclusion in the Time 1 assessment, potential subjects will be screened for eligibility requirements via an online survey. Once recruited, participants will finish the Time 1 assessment; then, the two experimental groups will receive art brut therapy once a week for 16 weeks. After the 16-week intervention, subjects will complete the Time 2 assessment. Every assessment will include both psychological and physiological measures. Symptom Checklists 90 (SCL-90) and the Positive Affect and Negative Affect Scale (PANAS) will be used to measure the psychological effects of art brut therapy in college students, while the level of cortisol in saliva samples and interleukin 6 (IL-6) in blood samples will be used to examine the physiological effects. Discussion This study will articulate the impact of art brut therapy on both psychological conditions and physiological markers associated with emotions, and it will also explore the feasibility and effectiveness of online art brut therapy. The results will determine the efficacy of a low-cost, easy-to-implement, accessible and engaging psychological health intervention for university students with emotional challenges during the COVID-19 pandemic. Trial registration Chinese Clinical Trial Registry, ChiCTR2200062802, August 19th, 2022.

Accurate Virus Identification with Interpretable Raman Signatures by Machine Learning (preprint)

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device coupled with label-free Raman Spectroscopy holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning approach applied to recognize the virus based on its Raman spectrum, which is used as a fingerprint. We present such a machine learning approach for analyzing Raman spectra of human and avian viruses. A Convolutional Neural Network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A vs. type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and non-enveloped viruses, and 99% accuracy for differentiating avian coronavirus (infectious bronchitis virus, IBV) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups (for example, amide, amino acid, carboxylic acid), we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses.

Accurate Virus Identification with Interpretable Raman Signatures by Machine Learning (preprint)

Rapid identification of newly emerging or circulating viruses is an important first step toward managing the public health response to potential outbreaks. A portable virus capture device coupled with label-free Raman Spectroscopy holds the promise of fast detection by rapidly obtaining the Raman signature of a virus followed by a machine learning approach applied to recognize the virus based on its Raman spectrum. In this paper, we present a machine learning analysis on Raman spectra of human and avian viruses. A Convolutional Neural Network (CNN) classifier specifically designed for spectral data achieves very high accuracy for a variety of virus type or subtype identification tasks. In particular, it achieves 99% accuracy for classifying influenza virus type A vs. type B, 96% accuracy for classifying four subtypes of influenza A, 95% accuracy for differentiating enveloped and non-enveloped viruses, and 99% for differentiating avian coronavirus (infectious bronchitis virus, IBV) from other avian viruses. Furthermore, interpretation of neural net responses in the trained CNN model using a full-gradient algorithm highlights Raman spectral ranges that are most important to virus identification. By correlating ML-selected salient Raman ranges with the signature ranges of known biomolecules and chemical functional groups (e.g. amide, amino acid, carboxylic acid) we verify that our ML model effectively recognizes the Raman signatures of proteins, lipids and other vital functional groups present in different viruses and uses a weighted combination of these signatures to identify viruses. The accurate and interpretable machine learning model developed for Raman virus identification presents promising potential in a real-time virus detection system. Significance Statement A portable micro-fluidic platform for virus capture promises rapid enrichment and label-free optical identification of viruses by Raman spectroscopy. A large Raman dataset collected on a variety of viruses enables the training of machine learning (ML) models capable of highly accurate and sensitive virus identification. The trained ML models can then be integrated with the portable device to provide real-time virus detection and identification capability. We validate this conceptual framework by presenting highly accurate virus type and subtype identification results using a convolutional neural network to classify Raman spectra of viruses.