Universal College

About: Universal College is a education organization based out in Las Piñas, Philippines. It is known for research contribution in the topics: Population & Health care. The organization has 567 authors who have published 450 publications receiving 1933 citations. The organization is also known as: Universal College of Nursing.

An Assistive Bot for Healthcare Using Deep Learning: Conversation-as-a-Service

Abstract: Gone are the days when software was used only for complex mathematical calculations or graphical motions alone. Today, it is software that has exponentially grown to become more powerful and more human—most obviously in applications such as ‘Chatbots.’ The year 2017 marks the Chatbot revolution in various industries like health, career, insurance, customer care support. Artificial intelligence (AI), which is the key player in enabling human-like behavior intelligently, is dramatically changing business. Chatbots, fueled by AI, are becoming a viable option for human–machine interaction. Deep learning algorithms have made it possible to build intelligent machine. In this research, we have developed a HealthBot using TensorFlow and Natural Language Processing (NLP) techniques. There is no denying that efficient patient engagement is a key challenge for all healthcare organizations and any company that can unravel this challenge can effectively earn high returns of investments. Chatbots are one of the major overhauls that hospitals can easily provide more customized care for patients while cutting down on the waiting period. The proposed HealthBot lists the common symptoms; then, based on user’s health issue it gets deeper into the conversations predicting the health problem of the user. Such bots are needed for today’s fast-moving population where they have no time to keep a tab on their health. Neural network implementation adds more accuracy to the responses. The proposed Chatbot model is a retrieval-based bot and of closed domain. Finally, the HealthBot is deployed on the Flask, a Python web development framework.

Catatonia in a Tertiary Care Center in Eastern Part of Nepal: A Descriptive Study

Abstract: Introduction: Catatonia is still an ill-understood phenomenology and we could not find any case based publications from Nepal. This study was undertaken to observe the proportion of catatonic patients in a year, to describe their frequencies, and to relate catatonia to mode of onset of catatonia, stressors and to diagnostic categories. Method: One-year prospective study was carried out in Psychiatry Ward of B. P. Koirala Institute of Health Sciences, Dharan. Socio-demographic variables were collected in structured Performa and Semi-Structured Performa was used for number of catatonic signs, life events, and mode of onset. Catatonia was screened and rated by Bush-Francis Catatonia Rating Scale. Psychiatric diagnoses were based on International Classification of Mental and Behavioral Disorder, Diagnostic and Research Guidelines, tenth version. Medical diagnoses were made by the consultant in Internal Medicine. Those who could not be admitted at least 24 hours for observation were not taken into study and 2 cases were excluded due to extreme of ages. Result: The proportions of patients with catatonia were 9.3% in psychiatric in-patients. Mutism was the most common sign and larger proportion had retarded catatonia. Mode of onset of catatonia, stressors, and disorders were not related. Medical and psychiatric catatonia could not be differentiated from the pattern of catatonic signs, even though echolalia occurred only in seizure disorder in our sample. Conclusion: The phenomenon of catatonia is common in our set-up. Mutism was the most common symptom. It is important to rule out organic etiology first. Depression is a common diagnosis with catatonia.

Pattern of Skin Diseases in Patients Visiting Universal College of Medical Sciences-Teaching Hospital (UCMS-TH) from the Three Districts of Terai Region in Nepal

Abstract: INTRODUCTION: The pattern of skin disease varies from country to country and in various regions within same country due to differences in socioeconomic and geographic factors. This study aimed to determine the pattern of skin disease from the three districts of Terai region in Nepal. MATERIALAND METHODS: This was retrospective study done from the hospital OPD patient's record of Universal college of Medical Sciences & Teaching Hospital (UCMS-TH), from 1st September 2011 to 31st August 2012. Patients from Rupandehi, Nawalparasi and Kapilvastu districts were taken. The diagnosis were entered in 15 categories like Acne, Alopecia Areata, Dermatophytosis, Drug reaction, Eczema, Leprosy, Lichen Planus, Melasma, Psoriasis, Pyoderma, Scabies, sexually transmitted diseses (STI), Urticaria, Viral infection and Vitiligo. Any diagnosis not in these categories, was kept at “Other” category. Monthly trend of disease was also analysed. RESULT: Total number of patients from Rupandehi, Kapilvastu and Nawalparasi districts were 12446 (89.3%), 661 (4.7%), 836 (6%) respectively. Dermatophytosis was the commonest 2003 (16.1%) in Rupandehi district, it was second in number in Nawalparasi and Kapilvastu. Eczema was the commonest in Kapilvastu and Nawalparasi district with 103 (15.6%) and 136 (16.3%) respectively. Eczema was second in number in Rupandehi district. Acne was third in number in Rupandehi and Nawalparasi but vitiligo was third common dermatosis recorded in Kapilvastu district. CONCLUSION: Dermatophytosis and Eczema are the most common dermatologic disorders in Terai region. DOI: http://dx.doi.org/10.3126/jucms.v2i3.11820 Journal of Universal College of Medical Sciences Vol.2(3) 2014: 3-8

Clinical vignette-based interactive discussion sessions: feedback from residents.

Abstract: Introduction A clinical vignette is a useful tool for teaching both clinical and basic sciences courses. The clinical vignette-based interactive discussion sessions were conducted for residents in the internal medicine department of Universal College of Medical Sciences( Bhairahawa, Nepal) with aim to link the residents to clinical practice setting. The objective of this study was to assess the feedback of participant. Methods The sessions were done five days a week between January 16 and February 26, 2019. Each session was between 45 and 60 minutes. The clinical vignettes related to internal medicine were downloaded using Google. Each vignette was divided into sections, related questions with responses were developed and the discussion was updated referring to the latest articles on subject. Eleven residents participated in the session. At the end of last session feedback was taken on a validated semi-structured questionnaire. The data was analyzed using SPSS version 21. Results Residents rated the clinical vignette-based interactive discussion sessions on the scale 1 = poor to 10= excellent; usefulness (9.45±1.04), content (9.27±0.90), relevance of session (9.18±1.08), facilitation (9.27±1.10), and overall (9.36±0.81). Participants rated the structure of vignettes discussed (3.73±0.47), the questions related to vignettes discussed (3.82±0.40), and discussion related to vignettes done (3.64±0.50) on a Likert scale 1-4 (4= extremely important, 3= moderately important, 2= slightly important, 1= not important). The two-way interaction, the approach toward differential diagnosis, diagnosis and management, choosing appropriate investigation, clinical relevancy of vignettes, boosts understanding, enhances thinking power and thinking outside the box, improving clinical approach and academic learning were among the strengths of sessions shared by residents. All residents proposed to continue these sessions and develop vignettes of our patients. The majority of the residents recommended conducting session on alternate days. Conclusion This method of learning allowing the residents to follow and construct clinical outcome in a logical and systematic sequence that may be applicable in real-life clinical practice settings. This method enhances the thinking power of residents and their problem-solving capacity.

Searchious: Locating missing people using an optimised face recognition algorithm

Abstract: Importance of face recognition systems has sped up in the last few decades. Face recognition is a part of biometric processing. Everyday hundreds of people go missing throughout the world. These people are either kidnapped, taken as slaves or forced to work underage, or beg on railway platforms, small shops or compelled into prostitution, human-trafficking or various other illegal activities. The posts of missing people are found in our day to day lives on social media platforms, news channels, newspapers etc. This research wok has been proposed to help them locate missing people in a easier way. The proposed tool, "Searchious" tends to reduce the time taken to trace the person and improve the process of finding the missing person. While Searchious can look for people who are missing, if a new face, which is not present in the database occurs, a new case can be filed for the same. Searchious has an Android application for the common citizens as well as a desktop software built using Python for the police stations by also including a face recognition algorithm based on KNN.