ABSTRACT
In today's post-covid culture, where everyone works from home, there is a huge possibility of serious long-term health problems. A lot of people have started taking up exercises at home and if done incorrectly, they can have major negative effects. Another one of the main contributors to these health issues is bad sitting posture, which is only exacerbated when working for hours on end. Hand gesture detection has many useful applications in elderly healthcare, automating actions and gesture-based presentations and games. To help users with these actions, our paper proposes pinpointing the points of the error to the user in real-time and in a lightweight manner for yoga posture correction. The incorrect positions shall be shown in real-time on top of the user's video feed to help them correct it properly. The user shall be told about when they are sitting in a bad position, and the overall bad posture time will also be shown for the session, which will provide the required information to the user. To further help users in a useful manner, our paper looks to augment the hand gesture detection feature with federated learning and personalization to avoid the common pitfall of privacy concerns, while still allowing users to customize their experience. The proposed library for the implementation of these tasks is the MediaPipe library. This library is one of the key components that makes the features lightweight and easy to use. The aforementioned library also looks to implement the features in real time with no lag while keeping the resource requirements as low as possible. © 2023 IEEE.
ABSTRACT
Background: Abnormal liver enzymes are frequently seen in the course of the COVID-19 in patients with no prior liver disease and has been frequent reason to consult Hepatology services during COVID-19 pandemic So far there is a relatively very poor characterization of this special population and we do not know whether mortality, severity of disease and health care burden is the same as described in the general population with COVID-19 Methods: We performed a retrospective, single-center study of 35 COVID-19 patients with no prior liver disease who developed significant liver enzymes elevation from April 1 to May 31, 2020 Inclusion criteria was nucleic acidconfirmed COVID-19 infection, no known history of prior liver disease, AST and/or ALT values at least 5 times the upper limit of normal and request for Hepatology Consult We recorded demographics (age, sex, BMI, race, ethnicity) comorbidities, laboratory values (CRP (C Reactive Protein), Procalcitonin, Fibrinogen, chemistry data), and clinical characteristics (hospital length of stay, Intensive Care Unit (ICU) admission, and mortality) for these patients The primary outcome was mortality Secondary outcomes were severity of disease defined as need for ICU admission and health care burden defined as an extended hospital stay beyond the average length of stay for the general COVID 19 population (14 days) Comparisons between the groups who reached primary and secondary end points were performed using unpaired t tests with Welch's correction and chi squared analysis (p-values <0 05) via the Prism statistical analysis software Results: Striking, from all the multiple variables analyzed, only the CRP was confirmed to be statistically significantly higher in deceased patients, ICU-admitted patients, and patients with extended hospital stay The mean CRP for deceased patients was 352 1+/-79 55 mg/L (p 0026) while the mean CRP for patients who lived was 277 7+/-133 8 mg/L (p 0026) Patients with ICU admissions had CRP mean of 309 9+/-105 5 mg/L (p 0016) versus 126 2 +/-111 4 mg/L (p 0016) without ICU admission Extended hospital stay patients had a CRP mean of 318 9+/-97 55 mg/L (p-value: 012) versus 201 2+/- 142 3 mg/L (p-value 012) for non-extended hospital stay patients As expected, patients requiring ICU admission or prolonged hospital stay had higher use of vasopressors, higher Alkaline Phosphatase peak and longer time interval to reach the ALT and Alkaline Phosphatase peak No other demographics, clinical or laboratory data were identified more frequent in patients who reached the end points in this specific COVID-19 group Conclusion: Patients with COVID-19 and moderate hepatocellular liver enzymes elevation and not known prior chronic liver disease is a specific subset of patients with risk factors for mortality, severity and length of stay different than the general population. These findings support the need for additional studies and prognostic modeling.