The impact of the COVID-19 health crisis on the mental health of the population requires the implementation of new primary screening strategies of mental health disorders to intervene in a timelier manner, and technology may provide solutions. We aimed to evaluate the usefulness of the mobile app Mentali (version 1.1.2; creators: Jorge Alfonso Solís Galván Sodel Vázquez Reyes, Margarita de la Luz Martínez Fierro, Perla Velasco Elizondo, Idalia Garza Veloz, Alejandro Mauricio González and Claudia Caldera Villalobos, Zacatecas, México) as a primary screening tool for anxiety and depression disorders in medical students and to assess the triggering risk factors. This was a descriptive and longitudinal study and included 155 Mexican medical students. Participants interacted with Mentali for 6 months. The mobile app integrated the Beck anxiety and depression inventories together with a mood module. At the end of the interaction, the students received psychological and psychiatric interventions to confirm their primary diagnoses. Symptoms of moderate/severe anxiety and depression were present in 62.6% and 54.6% of the studied population. When corroborating the diagnoses, Mentali obtained a sensitivity of 100%, 95%, and 43% to classify a mental health disorder, anxiety, and depression, respectively. The most important triggers found were as follows: belonging to a dysfunctional family, being introverted, and having suffered from bullying. The proportion of users with excellent/good mood decreased from 78.7% to 34.4% at the end of the semester, and the proportion of users who claimed to have bad/very bad mood increased from 7.4% to 34.4% at the end of the semester (p < 0.05). Mentali was useful for identifying users with anxiety and/or depression, and as an auxiliary tool to coordinate the provision of specialized interventions, allowing us to increase the proportion of patients who needed psychological care and received it by 30%. The efficacy of Mentali in identifying activities through time with an impact on the mood and mental health of the users was confirmed. Our results support the use of Mentali for the primary screening of mental health disorders in young adults, including medical students.

The current COVID-19 pandemic has completely changed people’s daily routines. This has had a big impact on mental health. In Mexico, medical school authorities are interested in understanding the mental health status of the student population to be able to provide support to students who may need help from a mental health specialist. The aim of this study was to develop a platform comprised of a mobile and web application called Mentali, to be used as an auxiliary tool for the detection of conditions such as anxiety and depression, as well as variations in mood, by analysis of the results of validated inventories. Following the Scrum software development methodology, Python, Dart and PHP programming languages were used for development of the application. This platform was used prospectively with 155 first year students taking part in the human medicine program. After 22 weeks, Mentali enabled the identification of 40 users with positive primary screening for anxiety and/or depression (45% for anxiety, 32.5% for both anxiety and depression, and 22.5% for altered mood). These students were contacted and referred to a psychologist; however, only 26 (65%) accepted psychological support. For all of these students a mental health disorder was confirmed. The results support the use of Mentali for the primary screening of anxiety and depression in young adults, including medical students.

Purpose: Radiotherapy treats cancers through precise delivery of radiation to target volumes. Radiotherapy treatment plans, prescribing the delivery of therapeutic radiation, are presently created primarily from clinical experience and application of clinical protocols through trial-and-error rather than standardized quantitative methods. We developed an informatics infrastructure and decision support system to assist during treatment plan creation by providing access to applicable retrospective radiotherapy cases. Methods: Radiotherapy treatment planning is based in part on tumor position and spatial relationships to surrounding structural anatomy. Our system data mines retrospective cases to identify cases and treatment plans with similar tumor position and surrounding anatomy (i.e., multi-organ-tumor constellation geometry) for clinicians to use as references during treatment plan creation. The system is based on a database of 390 DICOM RT dosimetry digital radiotherapy datasets with associated extracted quantitative features. Using data mining techniques, overall similarity between cases is calculated with features extracted from tumor volumes and organs at risk (OAR). Results: We implemented our radiotherapy treatment planning decision support system with a full-stack infrastructure, including a database of best practice retrospective cases, an algorithmic backend for feature extraction and similarity calculation, and a frontend web application for clinical use. Clinicians can upload current planning cases to the web application whereupon their similarity to knowledge base cases is calculated, and the most similar are presented to clinicians for selection as references during current treatment plan creation. Conclusions: This radiotherapy treatment planning decision support system, by providing access to geometrically similar retrospective best practice reference cases, presents a novel tool to improve treatment planning. Development of a full system infrastructure increases standardization, facilitates creation of high quality plans, and assists clinicians, particularly during the critical initial beam configuration stage.

Background: Predicting Alzheimer’s disease (AD)-related cognitive impairment (CI) among cognitively normal (CN) adults enables meaningful disease modification through early intervention and enrichment of clinical trials. Methods: A deep survival model is trained to predict CI conversion risk in 1415 CN adults from the National Alzheimer’s Coordinating Center. Converters’ (N = 212) and non-converters’ (N = 1203) baseline clinical measures and magnetic resonance images are used to estimate their conversion probability up to 22 years after baseline observation. Results: After 20-fold cross-validation, the model predicts conversion probability with a c-index of 0.88, classification accuracy of 75%, and AUC ROC of 0.89, outperforming previous machine learning models. Conclusions: This is one of few studies on the important challenge of predicting future CI among unimpaired subjects. Deep survival modeling can improve the identification of preclinical AD and suggests that uncertainty in AD risk estimation is due to potentially modifiable lifestyle factors.