Search

Tracheostomy in COVID-19 is a debatable topic, with guidelines and recommendations evolving with every wave. Tracheostomy can help early weaning and potentially increase the availability of ICU beds. The aim of our study was to determine the outcomes of patients undergoing tracheostomy at different timings. This was an ambispective observational descriptive longitudinal study of patients confirmed to have COVID-19 by real- time reverse transcriptase polymerase chain reaction (RT-PCR) admitted in the ICU and needed intubation for mechanical ventilation and underwent tracheostomy at a tertiary referral centre. This study was over a period of two months from May to June 2021. A total of 169 patients were admitted to the ICU for COVID-19 from May to June 2021 out of which 27 patients underwent open surgical tracheostomy. Study included almost equal number of male and female patients. The most frequent comorbidities were hypertension and diabetes. The majority of patients were between 5th and 7th decades of life (59.2%; 16 patients). The common indications for tracheostomy were acute respiratory distress syndrome, failure to wean from ventilation, sedation management, difficult airway, and persistent airway oedema. Five patients (18.5%) underwent tracheostomy on day 8, the maximum number on a single day. The earliest tracheostomy was done on day 3 and the latest on day 17 with variable results. There were 6 survivors out of 27, youngest being a 27-year-old female and oldest a 60-year-old male. Our study showed that there was no association of age, sex of the patients and presence of comorbid conditions with the timing of intubation. Clinical outcome of the patients also was not affected by the any of the socio clinical variables viz. age, sex of the patient, presence of comorbid conditions and timing of intubation. Tracheostomy in COVID-19 is an aerosol generating procedure; strict recommendations and guidelines need to be followed. [ABSTRACT FROM AUTHOR]

Objectives: Given the health risks associated with the garment manufacturing industry, it is important to periodically evaluate the health status of these workers. Our objectives in this study were to firstly assess the change in morbidity profile by comparing the recorded ailments of workers in a garment factory in a three year period and secondly to assess the change in their nutritional status (Body Mass Index) over a period of three years. Methodology: Retrospective cohort study design was used. Data from the periodic health check up for these employees in 2005 and 2002 was compared. Data was analyzed for 187 employees (males 19; female 168) who were present for the health check up of both 2005 and 2002. The chi-square test and comparison of change in percentages were used to determine significance of change in BMI. Results: Musculoskeletal ailments were the most common health problems in the garment factory. There was an increase in the number of workers with complaints of dental caries, refractive errors and respiratory ailments. There was an increase in the proportions of pre-obese, obese (class 1) and obese (class 2) workers and a decrease in the proportion of those underweight and normal. Analysis showed a significant increase in the Body Mass Index (BMI) of workers who were previously underweight (p=0.00), normal (p<0.001) or pre-obese (p=0.03). Conclusions: These findings, which are probably related to sedentary occupation, call for regular monitoring of BMI as well as dietary and lifestyle interventions for these workers. The findings also answer the call for factory-based interventions to improve workers' health. [ABSTRACT FROM AUTHOR]

Background: Predicting the likelihood of success of weight loss interventions using machine learning (ML) models may enhance intervention effectiveness by enabling timely and dynamic modification of intervention components for nonresponders to treatment. However, a lack of understanding and trust in these ML models impacts adoption among weight management experts. Recent advances in the field of explainable artificial intelligence enable the interpretation of ML models, yet it is unknown whether they enhance model understanding, trust, and adoption among weight management experts., Objective: This study aimed to build and evaluate an ML model that can predict 6-month weight loss success (ie, ≥7% weight loss) from 5 engagement and diet-related features collected over the initial 2 weeks of an intervention, to assess whether providing ML-based explanations increases weight management experts' agreement with ML model predictions, and to inform factors that influence the understanding and trust of ML models to advance explainability in early prediction of weight loss among weight management experts., Methods: We trained an ML model using the random forest (RF) algorithm and data from a 6-month weight loss intervention (N=419). We leveraged findings from existing explainability metrics to develop Prime Implicant Maintenance of Outcome (PRIMO), an interactive tool to understand predictions made by the RF model. We asked 14 weight management experts to predict hypothetical participants' weight loss success before and after using PRIMO. We compared PRIMO with 2 other explainability methods, one based on feature ranking and the other based on conditional probability. We used generalized linear mixed-effects models to evaluate participants' agreement with ML predictions and conducted likelihood ratio tests to examine the relationship between explainability methods and outcomes for nested models. We conducted guided interviews and thematic analysis to study the impact of our tool on experts' understanding and trust in the model., Results: Our RF model had 81% accuracy in the early prediction of weight loss success. Weight management experts were significantly more likely to agree with the model when using PRIMO (χ 2 =7.9; P=.02) compared with the other 2 methods with odds ratios of 2.52 (95% CI 0.91-7.69) and 3.95 (95% CI 1.50-11.76). From our study, we inferred that our software not only influenced experts' understanding and trust but also impacted decision-making. Several themes were identified through interviews: preference for multiple explanation types, need to visualize uncertainty in explanations provided by PRIMO, and need for model performance metrics on similar participant test instances., Conclusions: Our results show the potential for weight management experts to agree with the ML-based early prediction of success in weight loss treatment programs, enabling timely and dynamic modification of intervention components to enhance intervention effectiveness. Our findings provide methods for advancing the understandability and trust of ML models among weight management experts., (©Glenn J Fernandes, Arthur Choi, Jacob Michael Schauer, Angela F Pfammatter, Bonnie J Spring, Adnan Darwiche, Nabil I Alshurafa. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 06.09.2023.)

Researchers have been leveraging wearable cameras to both visually confirm and automatically detect individuals' eating habits. However, energy-intensive tasks such as continuously collecting and storing RGB images in memory, or running algorithms in real-time to automate detection of eating, greatly impacts battery life. Since eating moments are spread sparsely throughout the day, battery life can be mitigated by recording and processing data only when there is a high likelihood of eating. We present a framework comprising a golf-ball sized wearable device using a low-powered thermal sensor array and real-time activation algorithm that activates high-energy tasks when a hand-to-mouth gesture is confirmed by the thermal sensor array. The high-energy tasks tested are turning on the RGB camera (Trigger RGB mode) and running inference on an on-device machine learning model (Trigger ML mode). Our experimental setup involved the design of a wearable camera, 6 participants collecting 18 hours of data with and without eating, the implementation of a feeding gesture detection algorithm on-device, and measures of power saving using our activation method. Our activation algorithm demonstrates an average of at-least 31.5% increase in battery life time, with minimal drop of recall (5%) and without impacting the accuracy of detecting eating (a slight 4.1% increase in F1-Score).