ChatGPT gained widespread attention for its capabilities in natural language processing, enabling machines to assess human language inputs and generate complex, yet evolving answers. As large language models (LLMs) conti...ChatGPT gained widespread attention for its capabilities in natural language processing, enabling machines to assess human language inputs and generate complex, yet evolving answers. As large language models (LLMs) continue to develop, clear guidelines are needed to help healthcare providers and educators maximise their benefits while mitigating potential risks. This review assessed the utility and accuracy of applying ChatGPT in healthcare assistance, specifically in understanding clinical knowledge and guiding clinical practice and research. A search on PubMed/MEDLINE for ChatGPT-related articles from 30 November 2022 (ChatGPT's release date) to 14 March 2024 yielded 2690 articles. After screening and reviewing, 2141 articles were deemed relevant to the clinical and research domains. Of the articles, 60.3% were supportive of ChatGPT, highlighting its immense potential for automating routine tasks, enhancing decision-making processes and addressing complex challenges in health care. However, 0.9% were not supportive of ChatGPT's utilisation in its current form, given the unresolved ethical implications and concerns regarding accuracy, bias, privacy and legal. Additionally, 38.8% had an equivocal stance, suggesting for further research to fully understand the rapidly evolving capabilities and potential impacts of ChatGPT in healthcare. This review presents a newly created conceptual framework, the 'ABCD model', to facilitate a systematic approach for researchers and healthcare practitioners to navigate ChatGPT's strengths and limitations. The model aims to align the development and deployment of ChatGPT by providing guiding principles, which ChatGPT and other emerging LLMs should incorporate into further developments to ensure their suitable application in health care.
INTRODUCTION: Self-administered screening questionnaires are one of the key strategies to shorten diagnostic delay among patients with autoimmune rheumatic diseases (ARDs). However, most existing screening questionnaires...INTRODUCTION: Self-administered screening questionnaires are one of the key strategies to shorten diagnostic delay among patients with autoimmune rheumatic diseases (ARDs). However, most existing screening questionnaires for ARDs were developed to screen for one or a limited number of ARDs, and thus have limited utility when the goal is to screen for common ARDs. We aimed to develop a list of ARDs for population screening, and based on this, a list of manifestations to be assessed in a screening questionnaire for ARDs. METHODS: This study comprised two phases: Phase 1 involved the development of a list of ARDs through a modified Delphi study with accredited rheumatologists and Phase 2 involved the development of a list of manifestations through a modified nominal group technique with accredited rheumatologists, other healthcare professionals caring for patients with ARDs, and patients with ARDs. RESULTS: In Phase 1, 14 candidate ARDs were identified using a multipronged approach, ten of which were deemed necessary to be screened for in the general population, through three rounds of Delphi exercise. In Phase 2, 80 candidate manifestations of these ten ARDs were identified from a literature review. Of these, 59 manifestations were deemed necessary to be assessed in a screening questionnaire through one round of prenominal group dialogue and two rounds of nominal group discussion. CONCLUSION: Consensus-based lists of ARDs and their manifestations were developed in this study. They provide a basis for developing new ARD screening questionnaires to facilitate early diagnosis of ARDs in the general population.
INTRODUCTION: Total knee arthroplasty (TKA) remains the gold standard treatment for end-stage knee osteoarthritis. With rising TKA numbers, effective resource management, such as reducing length of stay, is crucial. Whil...INTRODUCTION: Total knee arthroplasty (TKA) remains the gold standard treatment for end-stage knee osteoarthritis. With rising TKA numbers, effective resource management, such as reducing length of stay, is crucial. While prior studies have focused on patient characteristics, this study aimed to investigate the influence of demographics and pre- and immediate postoperative patient-reported outcome measures (PROMs) on successful 24-h discharge using Enhanced Recovery After Surgery (ERAS) protocols. METHODS: Patients who underwent TKA with ERAS from August 2020 to July 2021 were followed up. Successful protocol completion was defined as discharge within 24 hours of surgery. Baseline characteristics and PROMs were recorded. Outcomes measures were compared between patients who successfully completed or failed the ERAS protocol, and variables were imputed into a binary logistic regression. RESULTS: Of 342 patients, 315 (92.1%) completed the ERAS protocol for TKA. Logistic regression analysis showed that higher postoperative pain scores and American Society of Anesthesiology (ASA) class > 2 significantly reduced the likelihood of passing the ERAS protocol (postoperative visual analogue scale odds ratio 0.742, P = 0.004; ASA > 2 odds ratio 0.196, P = 0.02). The model demonstrated satisfactory goodness of fit and accurately classified 80.1% of patients at the optimal cut-off. Receiver operating characteristic curve analysis showed good probability of discriminating between patients (area under the curve = 0.741). CONCLUSION: Immediate postoperative pain scores and ASA class may be useful adjuncts in predicting successful 24-h discharge after TKA using ERAS protocol.
Lee T, Teoh KJA, Acharyya S
… +8 more, Lee SY, Tan SM, Coliat CMD, Prabhakaran L, Goh CY, Azman NSB, Hou P, Pang EPH
Singapore Med J
· 2026 Jan · PMID 40674702
·
Full text
INTRODUCTION: Inhaler therapy is paramount in asthma management, yet non-adherence poses a significant challenge. This study investigates inhaler adherence patterns among adult asthma patients, employing the Test of Adhe...INTRODUCTION: Inhaler therapy is paramount in asthma management, yet non-adherence poses a significant challenge. This study investigates inhaler adherence patterns among adult asthma patients, employing the Test of Adherence to Inhalers (TAIs) questionnaire. METHODS: This cross-sectional study recruited 99 eligible patients from a specialist outpatient clinic over six months. The TAI questionnaire was administered to the patients. Data on asthma control test scores, medication possession ratio, and healthcare utilisation were collected. Statistical analyses were performed to examine the associations between adherence, patient characteristics, and clinical outcomes. RESULTS: More than half of the patients (68.7%) exhibited intermediate ( n = 23) or poor ( n = 45) adherence, with younger age associated with poorer adherence. Different patterns of non-compliance were identified; 38.8% ( n = 19) of patients with poor adherence showed deliberate non-compliance, whereas only 7.3% ( n = 3) with good adherence showed unconscious non-compliance. Surprisingly, patients with intermediate and poor adherence often achieved good asthma control, revealing potential challenges in outcome-based adherence assessments. A relatively higher but statistically non-significant proportion of patients with poor adherence had at least one hospitalisation or emergency department attendance due to asthma (42.2% with poor adherence vs. 35.5% with good adherence) or at least one asthma exacerbation requiring oral corticosteroid (64.4% with poor adherence vs. 48.4% with good adherence) in the past 12 months. CONCLUSION: This study provides insights into inhaler adherence among local adult asthma patients, identifying distinct adherence patterns and recognising potential complacency issues associated with traditional adherence assessments. Despite these limitations, our findings contribute to the optimisation of asthma care through a nuanced understanding of inhaler adherence.
INTRODUCTION: Procedures are frequently performed under regional or local anaesthesia, where patients maintain a level of consciousness. This has been associated with heightened pre- and intraprocedural anxiety levels, w...INTRODUCTION: Procedures are frequently performed under regional or local anaesthesia, where patients maintain a level of consciousness. This has been associated with heightened pre- and intraprocedural anxiety levels, which may increase the risk of emotional distress and worsen patient outcomes. Music therapy has been proposed as an effective non-pharmacological intervention to reduce anxiety levels. This is a pilot study aimed at evaluating the effect of music therapy on anxiety and perceived pain during intravitreal injections (IVI) in the Singaporean context. METHODS: Study participants were randomised into groups with and without music therapy. Anxiety levels were assessed using the Spielberger State-Trait Anxiety Inventory (state subscale) before and after IVI. The patients' perceptions of pain and discomfort were rated on a visual analogue scale. RESULTS: Fifty and 51 patients were assigned to the music therapy and control groups, respectively. After IVI, anxiety levels were lower in the music therapy group than the control group (-5.94 ± 10.81 vs. -5.02 ± 7.59; P = 0.62), although the difference was not statistically significant. The levels of pain and discomfort reported by patients in both groups were comparable. CONCLUSION: In the setting of IVIs, anxiety levels among patients receiving music therapy were reduced compared to those who had no music therapy, although the difference in anxiety levels was not statistically significant. Future studies should evaluate the impact of patient autonomy over the choice of music on the effectiveness of music therapy.
In Singapore, glucocorticoids are administered to pregnant women at risk of imminent preterm delivery. The primary desired benefit is maturation of the preterm fetal lung. The commonly used antenatal steroid regimen in S...In Singapore, glucocorticoids are administered to pregnant women at risk of imminent preterm delivery. The primary desired benefit is maturation of the preterm fetal lung. The commonly used antenatal steroid regimen in Singapore, two doses of 12 mg dexamethasone phosphate at a 12-h interval, is not widely used in other jurisdictions. There are important pharmacokinetic and pharmacodynamic differences between the glucocorticoids used to elicit fetal lung maturation. Acknowledging the range of society-endorsed clinical guidelines in worldwide use, we recommend that obstetric and neonatal services in Singapore work towards adopting a more widely accepted antenatal steroid dosing regimen: either two 11.4 mg maternal intramuscular injections of betamethasone (as betamethasone phosphate and betamethasone acetate), spaced by 24 h, or four 6 mg maternal intramuscular injections of dexamethasone phosphate spaced by 12 h.
Singapore Med J
· 2025 Jun · PMID 40489691
·
Publisher ↗
INTRODUCTION: There is currently no standardised approach to calculate and report proportion of days covered (PDC), a medication adherence measure. We aimed to assess adherence to antidiabetic medications by applying fou...INTRODUCTION: There is currently no standardised approach to calculate and report proportion of days covered (PDC), a medication adherence measure. We aimed to assess adherence to antidiabetic medications by applying four PDC models to a primary care database and examine the factors associated with medication adherence. METHODS: Four models were used to calculate PDC for 789 patients with diabetes mellitus (DM) using the average PDC method. Models P1 and P2 incorporated prescribed and dispensed data, whereas models D1 and D2 used dispensed data only. Models P1 and D1 used an interval-based method, whereas models P2 and D2 used a prescription-based method. Gender, age at recruitment, race, number of chronic diseases, years of DM, glycated haemoglobin (HbA1c) levels and number of antidiabetic medication classes were tested in a univariate analysis. Stepwise selection method was used in the multivariate logistic regression model. RESULTS: The proportion of adherent patients (PDC ≥80%) was 64.1% for model P1, 73.9% for P2, 66.5% for D1, and 87.3% for D2. Patients with PDC <80% were more likely to have HbA1c ≥9% (odds ratios 2.54 [P1], 2.69 [P2], 2.48 [D1], and 3.33 [D2]). Additionally, PDC <80% was associated with Malay or Indian ethnicity and having four or more chronic diseases. CONCLUSION: The PDC models that incorporate prescribed data and use interval-based methods may result in more patients being classified as having poor adherence. Compared to the other models, we postulate that model P2 may provide the most accurate estimate of adherence, as it takes into account the prescribers' intent by including prescribed data and changes in medication regimens by using prescription-based method.