Characteristics and clinical outcomes of patients with pre-delta, delta and omicron SARS-CoV-2 infection in Indonesia (2020-2023): a multicentre prospective cohort study.

Background: Limited data exist from southeast Asia on the impact of SARS-CoV-2 variants and inactivated vaccines on disease severity and death among patients hospitalised with COVID-19. Methods: A multicentre hospital-based prospective cohort was enrolled from September 2020 through January 2023, spanning pre-delta, delta, and omicron periods. The participant hospitals were conveniently sampled based on existing collaborations, site willingness and available study resources, and included six urban and two rural general hospitals from East Nusa Tenggara, Jakarta, and North Sumatra provinces. Factors associated with severe disease and day-28 mortality were examined using logistic and Cox regression. Findings: Among 822 participants, the age-adjusted percentage of severe disease was 26.8% (95% CI 22.7-30.9) for pre-delta, 50.1% (44.0-56.2) for delta, and 15.2% (9.7-20.7) for omicron. The odds of severe disease were 64% (18-84%) lower for omicron than delta (p < 0.001). One or more vaccine doses reduced the odds of severe disease by 89% (65-97%) for delta and 98% (91-100%) for omicron. Age-adjusted mortality was 11.9% (8.8-15.0) for pre-delta, 24.4% (18.8-29.9) for delta and 9.6% (5.2-14.0) for omicron. The day-28 cumulative incidence of death was lower for omicron (9.2% [5.6-13.9%]) than delta (28.6% [22.0-35.5%]) (p < 0.001). Severe disease on admission was the predominant prognostic factor for death (aHR34.0 [16.6-69.9] vs mild-or-moderate; p < 0.001). After controlling for disease severity on admission as an intermediate, the risk of death was 48% (32-60%) lower for omicron than delta (p < 0.001); and 51% (38-61%; p < 0.001) lower for vaccinated participants than unvaccinated participants overall, and 56% (37-69%; p < 0.001) for omicron, 46% (-5 to 73%; p = 0.070) for pre-delta (not estimable for delta). Interpretation: Infections by omicron variant resulted in less severe and fatal outcomes than delta in hospitalised patients in Indonesia. However, older, and unvaccinated individuals remained at greater risk of adverse outcomes. Funding: University of Oxford and Wellcome Trust.

How Well Do AI-Enabled Decision Support Systems Perform in Clinical Settings?

Real-world performance of machine learning (ML) models is crucial for safely and effectively embedding them into clinical decision support (CDS) systems. We examined evidence about the performance of contemporary ML-based CDS in clinical settings. A systematic search of four bibliographic databases identified 32 studies over a 5-year period. The CDS task, ML type, ML method and real-world performance was extracted and analysed. Most ML-based CDS supported image recognition and interpretation (n=12; 38%) and risk assessment (n=9; 28%). The majority used supervised learning (n=28; 88%) to train random forests (n=7; 22%) and convolutional neural networks (n=7; 22%). Only 12 studies reported real-world performance using heterogenous metrics; and performance degraded in clinical settings compared to model validation. The reporting of model performance is fundamental to ensuring safe and effective use of ML-based CDS in clinical settings. There remain opportunities to improve reporting.

Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: a scoping review.

OBJECTIVE: This study aims to summarize the research literature evaluating machine learning (ML)-based clinical decision support (CDS) systems in healthcare settings. MATERIALS AND METHODS: We conducted a review in accordance with the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta Analyses extension for Scoping Review). Four databases, including PubMed, Medline, Embase, and Scopus were searched for studies published from January 2016 to April 2021 evaluating the use of ML-based CDS in clinical settings. We extracted the study design, care setting, clinical task, CDS task, and ML method. The level of CDS autonomy was examined using a previously published 3-level classification based on the division of clinical tasks between the clinician and CDS; effects on decision-making, care delivery, and patient outcomes were summarized. RESULTS: Thirty-two studies evaluating the use of ML-based CDS in clinical settings were identified. All were undertaken in developed countries and largely in secondary and tertiary care settings. The most common clinical tasks supported by ML-based CDS were image recognition and interpretation (n = 12) and risk assessment (n = 9). The majority of studies examined assistive CDS (n = 23) which required clinicians to confirm or approve CDS recommendations for risk assessment in sepsis and for interpreting cancerous lesions in colonoscopy. Effects on decision-making, care delivery, and patient outcomes were mixed. CONCLUSION: ML-based CDS are being evaluated in many clinical areas. There remain many opportunities to apply and evaluate effects of ML-based CDS on decision-making, care delivery, and patient outcomes, particularly in resource-constrained settings.

Case Report: Left atrial myxoma with confirmed Delta variant COVID-19 infection, "to treat or withhold".

Primary cardiac tumors (PCTs) are extremely rare entities. More than half of PCTs are benign, with myxoma being the most common tumor. Generally, simple tumor resection is the treatment of choice for benign PCTs since it has promising results that yield low complication and recurrence rates. However, in the COVID-19 pandemic era, the mitigation protocols and/or concurrent COVID-19 infection should be taken into account in patient management for the best overall outcome. To our knowledge, this is the first case report of a patient with a left atrial myxoma and systemic embolism complication in the form of an ischemic stroke, with a concurrent confirmed COVID-19 delta variant infection.

The role of digital mobile technology in elderly health management among health care workers in Indonesia: Analysis of knowledge, attitudes, and practice.

Background: Technology, including information and communication technology (ICT), plays a significant role in the quality of health services. However, its application in elderly health services is still lacking. The aim of this study was to determine the knowledge of, attitudes toward, and practices of cell phone and mobile application use for elderly health care among Indonesian health care workers. Methods: This was a cross-sectional study conducted with health care workers in Jakarta, Indonesia. The potential subjects were contacted through instant messenger application and/or through conventional short message service or telephone calls from August through November 2020. Results: There were 134 subjects. All the subjects had used various health applications to assist with their daily work, including telemedicine (64.2%), guidelines (60.4%), and medical calculators (46.3%). However, 96.3% of the subjects were not aware of the existence of a health application for geriatric assessment. Furthermore, 98.5% of subjects thought that it is important to use ICT to manage geriatric patients, and 94.8% felt that comprehensive geriatric assessment (CGA) in digital form would help them manage geriatric patients better. Nevertheless, 35.10% of subjects had never applied CGA to their geriatric patients. Conclusions: The current health care system has begun to enter a period of using ICT in performing health services for geriatric patients. Nevertheless, only a few Indonesian health care workers were aware of or were using the geriatric mobile application. It is essential to improve the dissemination of geriatric health care and e-health literacy among them to improve the quality of elderly health care.

Accelerating Detection of Variants During COVID-19 Surges by Diverse Technological and Public Health Partnerships: A Case Study From Indonesia.

Early detection of Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2) variants and use of data for public health action requires a coordinated, rapid, and high throughput approach to whole genome sequencing (WGS). Currently, WGS output from many low- and middle-income countries (LMIC) has lagged. By fostering diverse partnerships and multiple sequencing technologies, Indonesia accelerated SARS-CoV-2 WGS uploads to GISAID from 1,210 in April 2021 to 5,791 in August 2021, an increase from 11 submissions per day between January to May, to 43 per day between June to August. Turn-around-time from specimen collection to submission decreased from 77 to 5 days, allowing for timely public health decisions. These changes were enabled by establishment of the National Genomic Surveillance Consortium, coordination between public and private sector laboratories with WGS capability, and diversification of sequencing platform technologies. Here we present how diversification on multiple levels enabled a rapid and significant increase of national WGS performance, with potentially valuable lessons for other LMICs.

The COVID-19 surge in Indonesia: what we learned and what to expect.

Through the implementation of a test and trace system, disciplined public health measures, the acceleration of vaccinations, and a genome surveillance programme, LMICs such as Indonesia can prevent future outbreaks and survive the COVID-19 pandemic. https://bit.ly/3JBBSie.

COVID-19 in Indonesia: Challenges and Multidisciplinary Perspectives for a Safe and Productive New Normal.

The COVID-19 pandemic has caused disruption in all aspects of life, and countries around the world have been combating this pandemic using multiple approaches. Success in one country does not guarantee a transferable approach to other countries with different contexts. This review describes the challenges of COVID-19 management in Indonesia as a populous, socially and culturally diverse, and archipelagic country. It aims to provide multidisciplinary perspectives for a safe, evidence-based, and productive new normal as well as a comprehensive and integrated actionable policy for COVID-19 control.