ABSTRACT
Background: Heart failure remains a considerable burden to healthcare in Asia. Early intervention, mainly using echocardiography, to assess cardiac function is crucial. However, due to limited resources and time, the procedure has become more challenging during the COVID-19 pandemic. On the other hand, studies have shown that artificial intelligence (AI) is highly potential in complementing the work of clinicians to diagnose heart failure accurately and rapidly. Methods: We systematically searched Europe PMC, ProQuest, Science Direct, PubMed, and IEEE following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and our inclusion and exclusion criteria. The 14 selected works of literature were then assessed for their quality and risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies). Results: A total of 2105 studies were retrieved, and 14 were included in the analysis. Five studies posed risks of bias. Nearly all studies included datasets in the form of 3D (three dimensional) or 2D (two dimensional) images, along with apical four-chamber (A4C) and apical two-chamber (A2C) being the most common echocardiography views used. The machine learning algorithm for each study differs, with the convolutional neural network as the most common method used. The accuracy varies from 57% to 99.3%. Conclusions: To conclude, current evidence suggests that the application of AI leads to a better and faster diagnosis of left heart failure through echocardiography. However, the presence of clinicians is still irreplaceable during diagnostic processes and overall clinical care;thus, AI only serves as complementary assistance for clinicians.
ABSTRACT
BACKGROUND: Many studies identified the risk factors and prognostic factors related to in-hospital COVID-19 mortality using sophisticated laboratory tests. Cost and the availability of supporting blood tests may be problematic in resource-limited settings. This multicenter cohort study was conducted to assess the factors associated with mortality of COVID-19 patients aged 18 years and older, based on history taking, physical examination, and simple blood tests to be used in resource-limited settings. METHODS: The study was conducted between July 2020 and January 2021 in five COVID-19 referral hospitals in Indonesia. Among 1048 confirmed cases of COVID-19, 160 (15%) died during hospitalization. RESULTS: Multivariate analysis showed eight predictors of in-hospital mortality, namely increased age, chronic kidney disease, chronic obstructive pulmonary disease, fatigue, dyspnea, altered mental status, neutrophil-lymphocyte ratio (NLR) >= 5.8, and severe-critical condition. This scoring system had an Area-under-the-curve (AUC) of 84.7%. With cut-off score of 6, the sensitivity was 76.3% and the specificity was 78.2%. CONCLUSION: The result of this practical prognostic scoring system may be a guide to decision making of physicians and help in the education of family members related to the possible outcome.
ABSTRACT
BACKGROUND: To date, no recommendations have been published on when and how to start again carrying out elective, non-urgent surgery on COVID-19-negative patients after the epidemic peak has been reached in a given country or region and the pressure on healthcare facilities, healthcare workers and resources has been released by so far that elective surgery procedures can be safely and ethically programmed again. This study aims to investigate whether elective orthopaedic surgery will increase the risk of developing COVID-19. MATERIALS AND METHODS: This was a combined retrospective and prospective studies performed at a national tertiary hospital in Jakarta, Indonesia. Subjects were patients who underwent elective orthopaedic surgeries at our institution from April to May 2020. Those who were previously infected with COVID-19 from polymerase chain reaction (PCR) reverse transcriptase (RT) examination obtained via nasopharynx and oropharynx swab, as well as those who were reluctant to participate were excluded from the study. RESULTS: A total of 35 subjects (mean age 32.89 ± 17.42) were recruited. Fifteen (42.9%) subjects were male, and 20 subjects (57.1%) were female. Mean duration of surgery was 240 min with the longest and shortest duration of 690 and 40 min, respectively. General anaesthesia was performed in the majority of cases in 18 surgeries (51.4%) with local anaesthesia as the least in 2 surgeries (5.7%). Length of stay of our study was 6 days of average. None of the patients developed symptoms suggestive of COVID-19 infection. CONCLUSION: We found that elective orthopaedic surgery may not be associated with increased cases of COVID-19 cases. However, our study was limited by short duration of follow-up. Further studies are required in order to investigate the affect of undergoing elective surgery and the number of COVID-19 cases.