More Like this

1. Computer-Based PTSD Assessment in VR Exposure Therapy

   https://doi.org/10.1007/978-3-030-59990-4_32  

   Tavabi, Leili; Poon, Anna; Rizzo, Albert Skip; Soleymani, Mohammad (October 2020, HCI International 2020 – Late Breaking Papers: Virtual and Augmented Reality)

   Stephanidis, Constantine; Chen, Jessie Y.; Fragomeni, Gino (Ed.)

   Post-traumatic stress disorder (PTSD) is a mental health condition affecting people who experienced a traumatic event. In addition to the clinical diagnostic criteria for PTSD, behavioral changes in voice, language, facial expression and head movement may occur. In this paper, we demonstrate how a machine learning model trained on a general population with self-reported PTSD scores can be used to provide behavioral metrics that could enhance the accuracy of the clinical diagnosis with patients. Both datasets were collected from a clinical interview conducted by a virtual agent (SimSensei) [10]. The clinical data was recorded from PTSD patients, who were victims of sexual assault, undergoing a VR exposure therapy. A recurrent neural network was trained on verbal, visual and vocal features to recognize PTSD, according to self-reported PCL-C scores [4]. We then performed decision fusion to fuse three modalities to recognize PTSD in patients with a clinical diagnosis, achieving an F1-score of 0.85. Our analysis demonstrates that machine-based PTSD assessment with self-reported PTSD scores can generalize across different groups and be deployed to assist diagnosis of PTSD. 

   more » « less
2. Cathepsin L and acute ischemic stroke: A mini-review

   https://doi.org/10.3389/fstro.2022.1050536  

   Ma, Linda; Wu, Silin; Gusdon, Aaron M.; Chen, Hua; Hu, Heng; Paz, Atzhiry S.; Aronowski, Jaroslaw; Savarraj, Jude P.; Kitagawa, Ryan S.; Choi, Huimahn A.; et al (November 2022, Frontiers in Stroke)

   Ischemic stroke is a serious cerebrovascular event that results in cell death, blood-brain barrier dysfunction, tissue degradation, and inflammation, often leading to permanent disability or death. As the incidence of ischemic stroke continues to rise globally, it is crucial to examine the mechanisms of the various proteins and molecules contributing to worsened patient outcome and recovery. Cathepsin L, a cysteine protease known for degrading tissues in lysosomes and elsewhere, may play a role in brain tissue loss and inflammation after stroke. Studies have suggested that cathepsin L appears in the ischemic core shortly after stroke is induced. Using immunohistochemical staining, mass spectrometry, and other assays, the increase of cathepsin L in the brain was correlated with extracellular matrix and perlecan degradation after ischemic stroke. Additionally, injection of a cathepsin L inhibitor significantly reduced brain infarct size and improved functional scores. More research is needed to elucidate cathepsin L's role in post-stroke inflammation and brain damage, in order to further explore the factors contributing to worsened patient outcome after ischemic stroke and work toward finding better therapeutic interventions. 

   more » « less
3. Effects of COVID-19 on Stress and Mental Health of Community College Pre-Engineering Students

   https://doi.org/10.1109/FIE56618.2022.9962570  

   Danowitz, Andrew; Beddoes, Kacey (January 2022, Frontiers in Education Annual Conference)

   This research full paper presents screening rates for mental health issues and life-stress events in engineering-focused community college students during the initial phases of the COVID-19 pandemic in the US. Specifically, it attempts to answer the following research questions: 1) What is the overall rate of various mental health conditions among engineering-focused community college students, 2) What effects has the pandemic had on baseline stress levels engineering-focused community college, and 3) What effects has the pandemic had on quality of life, such as sleep habits and financial security of engineering- focused community college students? Data for this paper was collected via survey from May–July 2020 and includes responses from 84 students at 24 community colleges. The survey itself was a compilation of several widely- used instruments for measuring overall mental health and stress levels in a population. These instruments include the Kessler-6 for psychological distress, the PHQ for anxiety, depression, and eating disorders, the PC-PTSD for PTSD-like symptoms, and the SRRS for inventorying stressful life events. Among the major findings, 32% of respondents reported a major change in financial situation, 27% reported loss of employment, and 13% reported ceasing formal schooling because of the COVID-19 pandemic. Additionally, 32% of respondents reported that the COVID-19 pandemic worsened their housing security situation, 38% reported that COVID-19 has worsened their food security situation, and 36% report that COVID-19 has decreased their ability to access instruction, course materials, or course supplies. Finally, of respondents who completed at least one mental health screening instrument, 70% screened positive for at least one potentially diagnosable condition, while only 9% reported ever receiving a mental health diagnosis. Index Terms—Community College, Mental Health, Disability, Accessibility, Equity, Inclusion, Wellness 

   more » « less
4. Using behavioral rhythms and multi-task learning to predict fine-grained symptoms of schizophrenia

   https://doi.org/10.1038/s41598-020-71689-1  

   Tseng, Vincent W.-S.; Sano, Akane; Ben-Zeev, Dror; Brian, Rachel; Campbell, Andrew T.; Hauser, Marta; Kane, John M.; Scherer, Emily A.; Wang, Rui; Wang, Weichen; et al (December 2020, Scientific Reports)

   Abstract Schizophrenia is a severe and complex psychiatric disorder with heterogeneous and dynamic multi-dimensional symptoms. Behavioral rhythms, such as sleep rhythm, are usually disrupted in people with schizophrenia. As such, behavioral rhythm sensing with smartphones and machine learning can help better understand and predict their symptoms. Our goal is to predict fine-grained symptom changes with interpretable models. We computed rhythm-based features from 61 participants with 6,132 days of data and used multi-task learning to predict their ecological momentary assessment scores for 10 different symptom items. By taking into account both the similarities and differences between different participants and symptoms, our multi-task learning models perform statistically significantly better than the models trained with single-task learning for predicting patients’ individual symptom trajectories, such as feeling depressed, social, and calm and hearing voices. We also found different subtypes for each of the symptoms by applying unsupervised clustering to the feature weights in the models. Taken together, compared to the features used in the previous studies, our rhythm features not only improved models’ prediction accuracy but also provided better interpretability for how patients’ behavioral rhythms and the rhythms of their environments influence their symptom conditions. This will enable both the patients and clinicians to monitor how these factors affect a patient’s condition and how to mitigate the influence of these factors. As such, we envision that our solution allows early detection and early intervention before a patient’s condition starts deteriorating without requiring extra effort from patients and clinicians. 

   more » « less
5. Noninvasive Modulation of the Subcallosal Cingulate and Depression With Focused Ultrasonic Waves

   https://doi.org/10.1016/j.biopsych.2024.09.029  

   Riis, Thomas S; Feldman, Daniel A; Kwon, Sarah S; Vonesh, Lily C; Koppelmans, Vincent; Brown, Jefferson R; Solzbacher, Daniela; Kubanek, Jan; Mickey, Brian J (April 2025, Biological Psychiatry)

   BACKGROUND: Severe forms of depression have been linked to excessive subcallosal cingulate cortex (SCC) ac- tivity. Stimulation of the SCC with surgically implanted electrodes can alleviate depression, but current noninvasive techniques cannot directly and selectively modulate deep targets. We developed a new noninvasive neuromodulation approach that can deliver low-intensity focused ultrasonic waves to the SCC. METHODS: Twenty-two individuals with treatment-resistant depression participated in a randomized, double-blind, sham-controlled study. Ultrasonic stimulation was delivered to the bilateral SCC during concurrent functional magnetic resonance imaging to quantify target engagement. Mood state was measured with the Sadness subscale of the Positive and Negative Affect Schedule before and after 40 minutes of real or sham SCC stimulation. Change in depression severity was measured with the 6-item Hamilton Depression Rating Scale at 24 hours and 7 days. RESULTS: Functional magnetic resonance imaging demonstrated a target-speci c decrease in SCC activity during stimulation (p = .028, n = 16). In 7 of 16 participants, SCC neuromodulation was detectable at the individual participant level with a single 10-minute scan (p , .05, small-volume correction). Mood and depression scores improved more with real than with sham stimulation. In the per-protocol sample (n = 19), real stimulation was superior to sham for 6-item Hamilton Depression Rating Scale scores at 24 hours and for Sadness scores (both p , .05, d . 1). Nonsigni cant trends were found in the intent-to-treat sample. CONCLUSIONS: This small pilot study indicates that ultrasonic stimulation modulates SCC activity and can rapidly reduce depressive symptoms. The capability to noninvasively and selectively target deep brain areas creates new possibilities for the future development of circuit-directed therapeutics and for the analysis of deep-brain circuit function in humans. 

   more » « less