Predicting Credit Ratings using Deep Learning Models - An Analysis of the Indian IT Industry

Due to the complexity of transactions and the availability of Big Data, many banks and financial institutions are reviewing their business models. Various tasks get involved in determining the credit worthiness like working with spreadsheets, manually gathering data from customers and corporations, etc. In this research paper, we aim to automate and analyze the credit ratings of the Information and technology industry in India. Various Deep-Learning models are incorporated to predict the credit rankings from highest to lowest separately for each company to find the best fit Margin, inventory valuation, etc., are the parameters that contribute to the credit rating predictions. The data collected for the study spans between the years FY-2015 to FY-2020. As per the research been carried out with efficiencies of different Deep Learning models been tested and compared, MLP gained the highest efficiency for predicting the same. This research contributes to identifying how we can predict the ratings for several IT companies in India based on their Financial risk, Business risk, Industrial risk, and Macroeconomic environment using various neural network models for better accuracy. Also it helps us understand the significance of Artificial Neural Networks in credit rating predictions using unstructured and real time Financial data consisting the influence of COVID-19 in Indian IT industry.

PATIENTS WITH CHRONIC HEPATITIS C COULD BE TREATED WITH SOFOSBUVIR/ VELPATASVIR FOR 12 WEEKS BY NON-SPECIALISTS: 2nd INTERIM ANALYSIS OF PROSPECTIVE STUDY HELIOS-3

Background: In France, prescribing authorization for hepatitis C virus (HCV) treatment has been expanded to all physicians including non-specialists working in addiction and psychiatric centers and in jails. Patient management includes a Test and Treat approach (TnT) to expedite treatment initiation and a pathway for severe patients followed-up by specialists. This is a descriptive, interim analysis of an ongoing study to assess the efficacy and safety of Sofosbuvir/Velpatasvir (SOF/VEL) for 12 weeks after prescription expansion in patients treated by specialists and non-specialists. Method(s): Included patients are HCV-infected adults following SOF/VEL-based regimens prescribed by primary care physicians and specialists. Data collected from available information in medical records include patient characteristics, number of days between positive PCR/fibrosis assessment and start of therapy, and proportion of patients with sustained virologic response (SVR) 12 weeks after treatment end. Qualitative variables are described as number and percentage (%);quantitative measures as mean (standard deviation;SD) or median (range) as indicated. Result(s): Table) As of January 2022, 286 patients had received at least one dose of SOF/VEL treatment;217 were managed by specialists and 69 by non-specialists. Median patient age was 53.14 years (19.8-88.7), 80 (28%) were F3/F4 and 185 (64.7%) were male. Occasional and excessive consumption of alcohol was reported in 43 (62.3%) and 87 (40.8 %) patients managed by specialists and non-specialists respectively. Current recreational drug use was reported more frequently in 37 patients (53.6%) managed by non-specialists and 40 patients (18.6%) managed by specialists. Mean number of days between SOF/VEL initiation and fibroscan and Fib 4 were 62.16 +/- 306.39 and 40.35 +/- 60.24, respectively. Median number of days between positive PCR and start of therapy was 89.19 +/- 311.17 and 60.65 +/- 80.71 for patients managed by specialists and non-specialists respectively, and only 2 were lost to follow-up. Among 167 eligible patients who achieved an SVR12, 124 (97.6%) [93.28;99.19] were managed by specialists and 40 (100.0%) [91.24;100.00] by non-specialists;according to fibrosis stage, 107 F0-F2 patients (100.0%) and 39 F3-F4 (92.9%) achieved SVR12. Overall, at least one adverse event was observed in 34 patients (11.9%), of which only 2 (0.7%) lead to drug withdrawal. Conclusion(s): This interim analysis describes a French study population benefiting from SOF/VEL in real world use after treatment prescription expansion. SVR12 rates were high, regardless of the type of patient management and stage of fibrosis suggesting that HCV patients could be treated by SOF/VEL for 12 weeks by non-specialists. Despite the COVID 19 situation this study suggested that HCV patient pathway could be more optimized regarding fibrosis assessment or genotype determination.

Quantification of biomaterial dispersion during otologic procedures and role of barrier drapes in Covid 2019 era - a laboratory model.

BACKGROUND: Aerosol generation during temporal bone surgery caries the risk of viral transmission. Steps to mitigate this problem are of particular importance during the coronavirus disease 2019 pandemic. OBJECTIVE: To quantify the effect of barrier draping on particulate material dispersion during temporal bone surgery. METHODS: The study involved a cadaveric model in a simulated operating theatre environment. Particle density and particle count for particles sized 1-10 µ were measured in a simulated operating theatre environment while drilling on a cadaveric temporal bone. The effect of barrier draping to decrease dispersion was recorded and analysed. RESULTS: Barrier draping decreased counts of particles smaller than 5 µ by a factor of 80 in the operating theatre environment. Both particle density and particle count showed a statistically significant reduction with barrier draping (p = 0.027). CONCLUSION: Simple barrier drapes were effective in decreasing particle density and particle count in the operating theatre model and can prevent infection in operating theatre personnel.