Background: Adolescence, a period of transition between childhood and adulthood, occupies a crucial position in the life of human beings. The primary causes of under nutrition in India are its large population, socio-economic differences and inadequate access to health facilities. Nutritional assessments among adolescents are important as they are the future parents and constitute a potentially susceptible group. Studies on the assessment of nutritional status of adolescents are less in number and a National database has not yet been developed. Methods: The present hospital based cross sectional study was conducted in year 2013 among 344 rural adolescents of 10-19 years age (166 boys and 178 girls) attending the outpatient department at rural health training centre (RHTC) Dhaura Tanda, district Bareilly, Uttar Pradesh, belonging to the Muslim and Hindu caste communities. The nutritional status was assessed in terms of under nutrition (weight-for-age below 3rd percentile), stunting (Height-for-age below 3rd percentile) and thinness (BMI-for-age below 5 th percentile). Diseases were accepted as such as diagnosed by pediatrician, skin specialist and medical officer. Results: The prevalence of underweight, stunting and thinness were found to be 32.8%, 19.5% and 26.7% respectively. The maximum prevalence of malnutrition was observed among early adolescents (28%-47%) and the most common morbidities were URTI (38.6%), diarrhea (16.8%), carbuncle / furuncle (16%) and scabies (9.30%). Conclusion:The study concluded that the most common morbidities among adolescents were related to nutrition and personal hygiene. Regular health programmes should focus to educate and promote health among adolescent.

<b><i>Introduction:</i></b> Brief, Web-based, and self-administered cognitive assessments hold promise for early detection of cognitive decline in individuals at risk for dementia. The current study describes the design, implementation, and convergent validity of a fWeb-based cognitive assessment tool, the Survey for Memory, Attention, and Reaction Time (SMART), for older adults. <b><i>Methods:</i></b> A community-dwelling sample of older adults (<i>n</i> = 69) was included, classified as cognitively intact (<i>n</i> = 44) or diagnosed with mild cognitive impairment (MCI, <i>n</i> = 25). Participants completed the SMART at home using their computer, tablet, or other Internet-connected device. The SMART consists of 4 face-valid cognitive tasks available in the public domain assessing visual memory, attention/processing speed, and executive functioning. Participants also completed a battery of standardized neuropsychological tests, a cognitive screener, and a daily function questionnaire. Primary SMART outcome measures consisted of subtest completion time (CT); secondary meta-metrics included outcomes indirectly assessed or calculated within the SMART (e.g., click count, total CT, time to complete practice items, and time of day the test was completed). <b><i>Results:</i></b> Regarding validity, total SMART CT, which includes time to complete test items, practice items, and directions, had the strongest relationship with global cognition (β = −0.47, <i>p</i> &#x3c; 0.01). Test item CT was significantly greater for the MCI group (<i>F =</i> 5.20, <i>p</i> = 0.026). Of the SMART tasks, the executive functioning subtests had the strongest relationship with cognitive status as compared to the attention/processing speed and visual memory subtests. The primary outcome measures demonstrated fair to excellent test-retest reliability (intraclass correlation coefficient = 0.50–0.76). <b><i>Conclusions:</i></b> This study provides preliminary evidence for the use of the SMART protocol as a feasible, reliable, and valid assessment method to monitor cognitive performance in cognitively intact and MCI older adults.

The goal of this project is to develop a novel and innovative mobile solution to address behavioral and psychological symptoms of dementia (BPSD) that occur in individuals with Alzheimer's. BPSD can include agitation, restlessness, aggression, apathy, obsessive-compulsive and repetitive behaviors, hallucinations, delusions, paranoia, and wandering. Alzheimer's currently affects 5.4 million adults in the United States and that number is projected to increase to 14 million by 2050. Almost 90% of all affected with AD experience BPSD, resulting in increased healthcare costs, heavier burden on caregivers, poor patient outcomes, early nursing home placement, long-term hospitalizations, and misuse of medications. Pharmacological support may have undesirable side effects such as sedation. Nonpharmacological interventions are alternative solutions that have shown to be effective without undesirable side effects. Music therapy has been found to lower BPSD symptoms significantly. Our study is based on combination of the reminiscence and the music therapies where past memorable events are recalled using prompts such as photos, videos, and music. We are proposing a mobile multimedia solution, a technical version of the combined reminiscence, and music therapies to prevent the occurrence of BPSD, especially for the rural population who have reduced access to dementia care services.

No abstract

INTRODUCTION AND OBJECTIVE: Current machine learning (ML) models are limited by poor interpretability, precluding their routine use in planning nerve-sparing at radical prostatectomy (RP). We aimed to leverage explainable artificial intelligence techniques to provide accurate, interpretable, and personalized predictions for side-specific extraprostatic extension (ssEPE).METHODS: A retrospective sample of 900 prostatic lobes (450 patients) from RP specimens at our institution between 2010 and 2020, was used as the training cohort. Features (ie: variables) included patient demographics, clinical, sonographic, and site-specific data from transrectal ultrasound-guided prostate biopsy. The label (ie: outcome) of interest was the presence of ssEPE in the prostatectomy specimen. A ten-fold stratified cross-validation method was performed to train a gradient-boosted model, optimize hyperparameters, and for internal validation. Our model was further externally validated using a testing cohort of 122 lobes (61 patients) from RP specimens at a separate institution between 2016 and 2020. An existing model from the literature which has the highest performance for predicting ssEPE was selected as the baseline model for comparison. Discriminative capability was quantified by area under receiver-operatingcharacteristic (AUROC) and precision-recall curve (AUPRC). Clinical utility was determined by decision curve analysis. Shapley Additive exPlanations were used to interpret the ML model's predictions.RESULTS: The incidence of ssEPE in the training and testing cohorts were 30.7 and 41.8%, respectively. Our model outperformed the baseline model with a mean AUROC of 0.81 vs 0.75 (p<0.01) and mean AUPRC of 0.69 vs 0.60, respectively, on cross-validation of the training cohort. Similarly, our model performed favourably on the testing cohort with an AUROC of 0.81 vs 0.76 (p[0.03) and AUPRC of 0.78 vs 0.72. On decision curve analysis, our model achieved a higher net benefit for threshold probabilities between 0.15 to 0.65. A web application incorporating our model was developed in which deidentified patient data can be inputted to generate an individualized ssEPE prostate map with annotated explanations to highlight which features had the greatest impact on model predictions (www.ssepe.ml).CONCLUSIONS: We have developed a user-friendly application that enables physicians without prior ML experience to assess ssEPE risk and understand the factors driving these predictions to aid surgical planning and patient counselling.