| 1. |
- Gupta, Rajesh, et al.
(author)
-
Infantile tremor syndrome : current perspectives
- 2019
-
In: Research and Reports in Tropical Medicine. - : DOVE MEDICAL PRESS LTD. - 1179-7282. ; 10, s. 103-108
-
Research review (peer-reviewed)abstract
- Infantile Tremor Syndrome (ITS) is a self-limiting clinical state characterized by tremors, anemia, pigmentary skin disease, regression of mental development, and hypotonia of muscles in a plump looking child. Tremors are coarse in character, decreased or disappeared in sleep and resolves within 4-6 weeks in its natural course. Various etiological factors as infectious, metabolic, nutritional have been hypothesized but none is conclusive. Consensus is developing on the role of Vitamin B12 deficiency in children with ITS but is still debatable. Empirical management of ITS children has been tried in the absence of exact etiology considering child as undernourished. Nutritional management includes supplementation of Iron, Calcium, Magnesium, Vitamin B12 and other multivitamins. Tremors can be managed with administration of propranolol most commonly or phenobarbitone, phenytoin, and carbamazepine.
|
|
| 2. |
- Rauniyar, Ashish, et al.
(author)
-
Federated learning for medical applications : A taxonomy, current trends, challenges, and future research directions
- 2022
-
Other publication (other academic/artistic)abstract
- With the advent of the Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML)/Deep Learning (DL) algorithms, the landscape of data-driven medical applications has emerged as a promising avenue for designing robust and scalable diagnostic and prognostic models from medical data. Consequently, the realm of data-driven medical applications has garnered significant attention spanning academia and industry, ushering in marked enhancements in healthcare delivery quality. Despite these strides, the adoption of AI-driven medical applications remains hindered by formidable challenges, including the arduous task of meeting security, privacy, and quality of service (QoS) standards. Recent developments in Federated Learning (FL) have made it possible to train complex machine-learned models in a distributed manner and have become an active research domain, particularly processing the medical data at the edge of the network in a decentralized way to preserve privacy and address security concerns. To this end, this survey paper highlights the current and future of FL technology in medical applications where data sharing is a significant burden. We delve into the contemporary research trends and their outcomes, unraveling the intricacies of designing reliable and scalable FL models. Our survey outlines the foundational statistical predicaments of FL, confronts device-related obstacles, delves into security challenges, and navigates the intricate terrain of privacy concerns, all while spotlighting its transformative potential within the medical domain. A primary focus of our study rests on medical applications, where we underscore the weighty burden of global cancer and illuminate the potency of FL in engendering computer-aided diagnosis tools that address this challenge with heightened efficacy. Further augmenting our discourse, recent literature has unveiled the inherent robustness and generalization of FL models compared to traditional data-driven medical applications. We hope that this review endeavors to serve as a checkpoint that sets forth the existing state-of-the-art works in a thorough manner and offers open problems and future research directions for this field.
|
|
| 3. |
- Rauniyar, Ashish, et al.
(author)
-
Federated Learning for Medical Applications : A Taxonomy, Current Trends, Challenges, and Future Research Directions
- 2024
-
In: IEEE Internet of Things Journal. - : Institute of Electrical and Electronics Engineers (IEEE). - 2327-4662. ; 11:5, s. 7374-7398
-
Journal article (peer-reviewed)abstract
- With the advent of the Internet of Things (IoT), artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms, the landscape of data-driven medical applications has emerged as a promising avenue for designing robust and scalable diagnostic and prognostic models from medical data. This has gained a lot of attention from both academia and industry, leading to significant improvements in healthcare quality. However, the adoption of AI-driven medical applications still faces tough challenges, including meeting security, privacy, and Quality-of-Service (QoS) standards. Recent developments in federated learning (FL) have made it possible to train complex machine-learned models in a distributed manner and have become an active research domain, particularly processing the medical data at the edge of the network in a decentralized way to preserve privacy and address security concerns. To this end, in this article, we explore the present and future of FL technology in medical applications where data sharing is a significant challenge. We delve into the current research trends and their outcomes, unraveling the complexities of designing reliable and scalable FL models. This article outlines the fundamental statistical issues in FL, tackles device-related problems, addresses security challenges, and navigates the complexity of privacy concerns, all while highlighting its transformative potential in the medical field. Our study primarily focuses on medical applications of FL, particularly in the context of global cancer diagnosis. We highlight the potential of FL to enable computer-aided diagnosis tools that address this challenge with greater effectiveness than traditional data-driven methods. Recent literature has shown that FL models are robust and generalize well to new data, which is essential for medical applications. We hope that this comprehensive review will serve as a checkpoint for the field, summarizing the current state of the art and identifying open problems and future research directions.
|
|
| 4. |
- Rawat, Ashish, et al.
(author)
-
Drug Adverse Event Detection Using Text-Based Convolutional Neural Networks (TextCNN) Technique
- 2022
-
In: Electronics. - : MDPI. - 2079-9292. ; 11:20
-
Journal article (peer-reviewed)abstract
- With the rapid advancement in healthcare, there has been exponential growth in the healthcare records stored in large databases to help researchers, clinicians, and medical practitioner’s for optimal patient care, research, and trials. Since these studies and records are lengthy and time consuming for clinicians and medical practitioners, there is a demand for new, fast, and intelligent medical information retrieval methods. The present study is a part of the project which aims to design an intelligent medical information retrieval and summarization system. The whole system comprises three main modules, namely adverse drug event classification (ADEC), medical named entity recognition (MNER), and multi-model text summarization (MMTS). In the current study, we are presenting the design of the ADEC module for classification tasks, where basic machine learning (ML) and deep learning (DL) techniques, such as logistic regression (LR), decision tree (DT), and text-based convolutional neural network (TextCNN) are employed. In order to perform the extraction of features from the text data, TF-IDF and Word2Vec models are employed. To achieve the best performance of the overall system for efficient information retrieval and summarization, an ensemble strategy is employed, where predictions of the selected base models are integrated to boost the robustness of one model. The performance results of all the models are recorded as promising. TextCNN, with an accuracy of 89%, performs better than the conventional machine learning approaches, i.e., LR and DT with accuracies of 85% and 77%, respectively. Furthermore, the proposed TextCNN outperforms the existing adverse drug event classification approaches, achieving precision, recall, and an F1 score of 87%, 91%, and 89%, respectively.
|
|
| 5. |
- Rawat, Angeli, et al.
(author)
-
The contribution of community health systems to resilience : case study of the response to the 2015 earthquake in Nepal
- 2023
-
In: Journal of Global Health. - : International Society of Global Health. - 2047-2978 .- 2047-2986. ; 13
-
Journal article (peer-reviewed)abstract
- Background Understanding how to build resilience in health systems is essen-tial to ensuring countries can respond to shocks and has become increasingly important in the context of climate change. The 2015 earthquake in Nepal of-fered an opportunity to capture lessons learned and advance our understanding of resilience. Community members, especially female community health volun-teers (FCHVs), were central to the response. We aimed to describe the successes and challenges with building resilience in community-based health systems after the earthquake response from multiple perspectives within the health system.Methods Key informant interviews and focus group discussions were utilised. Participants included FCHVs, primary healthcare workers, community lead-ers and mothers, district health managers, representatives from the Ministry of Health and Population, multilateral health organisations, bilateral develop-ment partners, local non-governmental organisations, community-based organ-isations, and international non-governmental organisations. We used thematic content analysis to identify emerging themes.Results Seventy-seven people participated in the study in September 2016 from communities (n = 53, 69%), districts (n = 8, 10%), and national levels (n = 16, 21%). Strong coordination, international and national support, and communi-ty engagement and participation were reported as successes of the earthquake response. Challenges included a lack of preparedness and supplies, a lack of earthquake-resistant infrastructure, and the centralisation of the response. FCH-Vs continued to work, despite being victims of the earthquake themselves. Facil-itators of the continuation of the FCHVs' duties included their strong ties with the communities and facilities, international support, and the ability to mobilise existing community resources. Barriers included fear, communities' attitudes, high workloads, large geographic distances, and difficult geography. Participants identified the importance of having strong, connected, and supported commu-nities, adaptable funding and policies, and decentralised decision-making with-in strong health systems. Conclusions Building resilience in community-based health systems must start with strong communities that are prepared, trained, equipped, and empowered. Health systems must be decentralised and adaptable, with strong coordination and leadership. Capable community health workers such as FCHVs were an important part of building resilience during the earthquake. These lessons can assist countries in strengthening decentralised health systems to better respond to a multitude of shocks, while still providing essential health services for com-munities.
|
|
| 6. |
- Abbafati, Cristiana, et al.
(author)
-
- 2020
-
Journal article (peer-reviewed)
|
|
