Our members are committed to develop affordable detection and prognosis using blood. We are developing cognitive computing based methods to identify as well as use markers for detection of disorders using blood samples. In addition, we are trying develop methods to characterise diseases like cancer to guide therapeutics.
Recent trends in hospital and some community based surveys show increase in resistance towards antimicrobials like antibiotics and antivirals. Research is needed to characterise antimicrobial use and cause of development of antimicrobial resistance, to decide interventional strategies. Our faculty members are involved in nation-wide studies of trend in antimicrobial resistance
OIn addition to basic research, the current trend in diagnostics and prognostics shows heavy dependence on the use of genomic data profiling. Genome profiles of various kinds including transcriptome, epigenome and structural variant are being regularly involved. We use our expertise and experience in profiling as well as analytics of genomics profiles for various purpose.
Currently vast amount of information related to public health is available in literature. We try to process such information using AI and language processing approach to find clear dependencies among different types of morbidities and trends in health. In addition we mine literature for finding links between symptoms and disorders and therapeutics, to ultimately help experts.
Developing interactive training and mentoring session for community health workers in india (ASHAs) using mobile phones and interactive voice response systems for better public healthcare in rural communities
This study focuses on leveraging protein structure readouts to predict cancer drivers for precision medicine applications. By analysing genetic mutations and their impact on protein structures, researchers aim to identify key drivers of cancer development. This approach holds promise for developing targeted therapies tailored to individual patients, enhancing the efficacy of cancer treatment through precision medicine strategies
ECG-iCOVIDNet is an AI model that identifies changes in ECG signals of post-COVID patients compared to normal individuals. It provides explainability for both patient and population-level differences, aiding in understanding and managing cardiac complications in post-COVID individuals.
Making and validating indicator for prognostic outcomes in critical care and emergency settings. Using data from large number of ICU-stays of adult patients and deep learning models to make useful insights