FAIM: Fairness-aware interpretable modeling for trustworthy machine learning in healthcare.

The escalating integration of machine learning in high-stakes fields such as healthcare raises substantial concerns about model fairness. We propose an interpretable framework, fairness-aware interpretable modeling (FAIM), to improve model fairness without compromising performance, featuring an interactive interface to identify a "fairer" model from a set of high-performing models and promoting the integration of data-driven evidence and clinical expertise to enhance contextualized fairness. We demonstrate FAIM's value in reducing intersectional biases arising from race and sex by predicting hospital admission with two real-world databases, the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) and the database collected from Singapore General Hospital Emergency Department (SGH-ED).

Disparities in clinical studies of AI enabled applications from a global perspective.

Artificial intelligence (AI) has been extensively researched in medicine, but its practical application remains limited. Meanwhile, there are various disparities in existing AI-enabled clinical studies, which pose a challenge to global health equity. In this study, we conducted an in-depth analysis of the geo-economic distribution of 159 AI-enabled clinical studies, as well as the gender disparities among these studies.

Comparison of the Quality of Discharge Letters Written by Large Language Models and Junior Clinicians: Single-Blinded Study.

Background: Discharge letters are a critical component in the continuity of care between specialists and primary care providers. However, these letters are time-consuming to write, underprioritized in comparison to direct clinical care, and are often tasked to junior doctors. Prior studies assessing the quality of discharge summaries written for inpatient hospital admissions show inadequacies in many domains.

Novel artificial intelligence algorithms for diabetic retinopathy and diabetic macular edema.

Background: Diabetic retinopathy (DR) and diabetic macular edema (DME) are major causes of visual impairment that challenge global vision health. New strategies are needed to tackle these growing global health problems, and the integration of artificial intelligence (AI) into ophthalmology has the potential to revolutionize DR and DME management to meet these challenges.

Main Text: This review discusses the latest AI-driven methodologies in the context of DR and DME in terms of disease identification, patient-specific disease profiling, and short-term and long-term management.

Comparing Open-Access Database and Traditional Intensive Care Studies Using Machine Learning: Bibliometric Analysis Study.

Background: Intensive care research has predominantly relied on conventional methods like randomized controlled trials. However, the increasing popularity of open-access, free databases in the past decade has opened new avenues for research, offering fresh insights. Leveraging machine learning (ML) techniques enables the analysis of trends in a vast number of studies.

Preoperative anemia in older individuals undergoing major abdominal surgery is associated with early postoperative morbidity: a prospective observational study.

Purpose: Preoperative anemia is associated with poor postoperative outcomes. Older patients have limited physiologic reserves, which renders them vulnerable to the stress of major abdominal surgery. We aimed to determine if the severity of preoperative anemia is associated with early postoperative morbidity among older patients undergoing major abdominal surgery.

Prehabilitation programs - a systematic review of the economic evidence.

Introduction: Prehabilitation, which involves improving a patient's physical and psychological condition before surgery, has shown potential benefits but has yet to be extensively studied from an economic perspective. To address this gap, a systematic review was conducted to summarize existing economic evaluations of prehabilitation interventions.

Methods: The PRISMA Protocols 2015 checklist was followed.

The SingHealth Perioperative and Anesthesia Subject Area Registry (PASAR), a large-scale perioperative data mart and registry.

Background: To enhance perioperative outcomes, a perioperative registry that integrates high-quality real-world data throughout the perioperative period is essential. Singapore General Hospital established the Perioperative and Anesthesia Subject Area Registry (PASAR) to unify data from the preoperative, intraoperative, and postoperative stages. This study presents the methodology employed to create this database.

Improving the accuracy of revised cardiac risk index with HbA1C: Hemoglobin ratio (HH ratio) - A retrospective cohort study.

Background: The current Lee's Revised cardiac risk index (RCRI) was created in 1999. Validation studies have found RCRI to be only moderately discriminant. The "Diabetes Mellitus on insulin" component of the score does not accurately reflect the severity of the disease.

Discordant American Society of Anesthesiologists Physical Status Classification between anesthesiologists and surgeons and its correlation with adverse patient outcomes.

The American Society of Anesthesiologists Physical Status Classification (ASA) is used for communication of patient health status, risk scoring, benchmarking and financial claims. Prior studies using hypothetical scenarios have shown poor concordance of ASA classification among healthcare providers. There is a paucity of studies using clinical data, and of clinical factors or patient outcomes associated with discordant classification.

Research on natural products from traditional Chinese medicine in the treatment of myocardial ischemia-reperfusion injury.

Myocardial ischemia-reperfusion injury (MIRI) is a complicated pathologic process that involves multiple factors including oxidative stress (free radical damage), inflammatory response, calcium overloading, and apoptosis in cardiomyocytes. According to Traditional Chinese Medicine (TCM), MIRI belongs to the categories of "chest numbness", "palpitations" and "angina pectoris". Present data indicate that the application of TCM in myocardial ischemia-reperfusion injury is promising and continues to attract research attention.

Incidence and risk factors of delirium in post-anaesthesia care unit.

Introduction: Post-anaesthesia care unit (PACU) delirium is a potentially preventable condition that results in a significant long-term effect. In a multicentre prospective cohort study, we investigate the incidence and risk factors of postoperative delirium in elderly patients undergoing major non-cardiac surgery.

Methods: Patients were consented and recruited from 4 major hospitals in Singapore.

Clinical study on the treatment of chronic heart failure with a novel D-shant atrium shunt device.

Background: Atrial septal shunt devices might improve hospitalizations and also prognosis in heart failure with increased pulmonary pressures due to left heart diseases. In recent years, atrial shunt devices have been used for the treatment of chronic heart failure, but there remains a lack of clinical experience. This study aimed to analyse the therapeutic effect of a novel type of atrial shunt on chronic heart failure.

Risk factors of post-anaesthesia care unit delirium in patients undergoing non-cardiac surgery in Singapore.

Introduction: Post-anaesthesia care unit (PACU) delirium affects 5%-45% of patients after surgery and is associated with postoperative delirium and increased mortality. Up to 40% of PACU delirium is preventable, but it remains under-recognised due to a lack of awareness of its diagnosis. The nursing delirium screening scale (Nu-DESC) has been validated for diagnosing PACU delirium, but is not routinely used locally.

The impact of preoperative glycated hemoglobin (HbA1c) on postoperative complications after elective major abdominal surgery: a meta-analysis.

Background: Diabetes is a risk factor for postoperative complications. Previous meta-analyses have shown that elevated glycated hemoglobin (HbA1c) levels are associated with postoperative complications in various surgical populations. However, this is the first meta-analysis to investigate the association between preoperative HbA1c levels and postoperative complications in patients undergoing elective major abdominal surgery.

Piriformis Pyomyositis Presenting as Migratory Hip to Knee Pain: A Case Report.

Case: The authors report a case of piriformis pyomyositis in a teenage female patient with fever and left hip pain. Her pain migrated to the knee with concurrent near resolution of hip pain. Imaging revealed an abscess in the left piriformis with pus tracking along the sciatic nerve sheath.

Clinical characteristics on admission predict in-hospital fatal outcome in patients aged ≥75 years with novel coronavirus disease (COVID-19): a retrospective cohort study.

Background: Novel coronavirus disease 2019 (COVID-19) has become a worldwide pandemic and precise fatality data by age group is needed urgently. This study to delineate the clinical characteristics and outcome of COVID-19 patients aged ≥75 years and identify the risk factors of in-hospital death.

Methods: A total of 141 consecutive patients aged ≥75 years who were admitted to the hospital between 12th and 19th February 2020.

A Newly Proposed HbA1C-Hemoglobin Ratio - A Better Predictor of Outcomes in Cardiac Surgery When Compared to HbA1C and Anemia Alone.

HbA1C's predictive value for postoperative complications in cardiac surgery has been mixed. Studies did not account for HbA1C being over-read in anemic patients. This study proposes a novel way of using a ratio of HbA1C over hemoglobin (HH ratio).

Impact of preoperative HbA1c on postoperative complications after elective major abdominal surgery: a systematic review protocol.

Introduction: Diabetes has an increasing worldwide prevalence. It is known to be a predisposing factor for postoperative complications. Preoperative glycaemic control strategies should be pursued as glycaemic control could serve as a modifiable risk factor.