Assessing the Utility, Impact, and Adoption Challenges of an Artificial Intelligence-Enabled Prescription Advisory Tool for Type 2 Diabetes Management: Qualitative Study.

BACKGROUND: The clinical management of type 2 diabetes mellitus (T2DM) presents a significant challenge due to the constantly evolving clinical practice guidelines and growing array of drug classes available. Evidence suggests that artificial intelligence (AI)-enabled clinical decision support systems (CDSSs) have proven to be effective in assisting clinicians with informed decision-making. Despite the merits of AI-driven CDSSs, a significant research gap exists concerning the early-stage implementation and adoption of AI-enabled CDSSs in T2DM management. OBJECTIVE: This study aimed to explore the perspectives of clinicians on the use and impact of the AI-enabled Prescription Advisory (APA) tool, developed using a multi-institution diabetes registry and implemented in specialist endocrinology clinics, and the challenges to its adoption and application. METHODS: We conducted focus group discussions using a semistructured interview guide with purposively selected endocrinologists from a tertiary hospital. The focus group discussions were audio-recorded and transcribed verbatim. Data were thematically analyzed. RESULTS: A total of 13 clinicians participated in 4 focus group discussions. Our findings suggest that the APA tool offered several useful features to assist clinicians in effectively managing T2DM. Specifically, clinicians viewed the AI-generated medication alterations as a good knowledge resource in supporting the clinician's decision-making on drug modifications at the point of care, particularly for patients with comorbidities. The complication risk prediction was seen as positively impacting patient care by facilitating early doctor-patient communication and initiating prompt clinical responses. However, the interpretability of the risk scores, concerns about overreliance and automation bias, and issues surrounding accountability and liability hindered the adoption of the APA tool in clinical practice. CONCLUSIONS: Although the APA tool holds great potential as a valuable resource for improving patient care, further efforts are required to address clinicians' concerns and improve the tool's acceptance and applicability in relevant contexts.

Application of artificial intelligence in the assessment of thyroid eye disease (TED) - a scoping review.

Background: There is emerging evidence which suggests the utility of artificial intelligence (AI) in the diagnostic assessment and pre-treatment evaluation of thyroid eye disease (TED). This scoping review aims to (1) identify the extent of the available evidence (2) provide an in-depth analysis of AI research methodology of the studies included in the review (3) Identify knowledge gaps pertaining to research in this area. Methods: This review was performed according to the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement (PRISMA). We quantify the diagnostic accuracy of AI models in the field of TED assessment and appraise the quality of these studies using the modified QUADAS-2 tool. Results: A total of 13 studies were included in this review. The most common AI models used in these studies are convolutional neural networks (CNN). The majority of the studies compared algorithm performance against healthcare professionals. The overall risk of bias and applicability using the modified Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool led to most of the studies being classified as low risk, although higher deficiency was noted in the risk of bias in flow and timing. Conclusions: While the results of the review showed high diagnostic accuracy of the AI models in identifying features of TED relevant to disease assessment, deficiencies in study design causing study bias and compromising study applicability were noted. Moving forward, limitations and challenges inherent to machine learning should be addressed with improved standardized guidance around study design, reporting, and legislative framework.

Artificial intelligence innovation in healthcare: Relevance of reporting guidelines for clinical translation from bench to bedside.

Artificial intelligence (AI) and digital innovation are transforming healthcare. Technologies such as machine learning in image analysis, natural language processing in medical chatbots and electronic medical record extraction have the potential to improve screening, diagnostics and prognostication, leading to precision medicine and preventive health. However, it is crucial to ensure that AI research is conducted with scientific rigour to facilitate clinical implementation. Therefore, reporting guidelines have been developed to standardise and streamline the development and validation of AI technologies in health. This commentary proposes a structured approach to utilise these reporting guidelines for the translation of promising AI techniques from research and development into clinical translation, and eventual widespread implementation from bench to bedside.

Adherence to dosing schedule of denosumab therapy for osteoporosis during COVID-19 lockdown: an electronic medical record and pharmacy claims database study from Asia.

COVID-19 lockdowns have impacted management of chronic diseases such as osteoporosis. Adherence to the 6-monthly dosing schedule of denosumab, the parenteral anti-osteoporosis medication most often used in Singapore, was significantly reduced during the lockdown period compared to that during pre-COVID-19 times. Patients managed by endocrinologists were more likely to be adherent. PURPOSE: No study thus far has quantified actual adherence rates to anti-osteoporosis therapy with denosumab during COVID-19 or explored factors associated with it. We aimed to estimate the adherence rates to denosumab in Singaporean men and women during COVID-19 lockdown and to compare it with those during the pre-COVID-19 period. METHOD: We conducted this retrospective, electronic medical records, and pharmacy claims database study at Singapore General Hospital, the largest hospital in the country. Patients initiated on subcutaneous denosumab between August 2019 and December 2019 and were thus scheduled to receive the second dose during the COVID-19 first-wave period from February 2020 to June 2020 (lockdown group) were analyzed, as were patients initiated anytime on denosumab between September 2011 and December 2018 (pre-COVID-19 group). Data extracted from the hospital's electronic prescription platform and patients' pharmacy purchase records were matched. Adherence was defined as being punctual (with an allowable delay of up to 4 weeks) with the second dose scheduled 6 months from the 1st dose. A sensitivity analysis with an allowable delay up to 8 weeks was also performed. We compared the adherence rates between the two periods and explored factors associated with adherence. RESULTS: A total of 768 and 1458 patients respectively during the lockdown and pre-COVID-19 periods were analyzed. The mean adherence rate during lockdown was 63.9%. The odds of being adherent during lockdown were higher if patients were managed by endocrinologists as opposed to those by other specialists [OR 2.516 (95% CI: 1.836-3.448); p < 0.001]. Adherence rates during the pre-COVID-19 period was 75.4%. Overall, the odds of being adherent to denosumab was significantly lower during lockdown than that during the pre-COVID-19 period [OR 0.525 (95% CI 0.430-0.640); p < 0.001], and odds of being adherent were higher if patients were managed by endocrinologists than if they were managed by other specialists (OR 1.765 (95% CI: 1.444-2.158; p < 0.001). CONCLUSION: Adherence to denosumab was significantly lower during COVID-19 lockdown than the pre-COVID-19 period. The odds of being adherent were higher in patients managed by endocrinologists. Whether healthcare providers from certain specialties spend more time counselling and educating patients about the importance of adherence to osteoporosis medications needs to be explored further.

De Novo Extra-Thyroidal Manifestations of Graves' Disease presenting 16 Years after Total Thyroidectomy for Thyroid Cancer.

We present a 61-year-old Chinese female who had a history of angioinvasive follicular thyroid cancer (FTC) treated with total thyroidectomy 16 years ago, without radioactive iodine (RAI) treatment who now presents with de novo pretibial myxedema (PTM) followed by active severe Graves' ophthalmopathy (GO) requiring pulse steroids and radiotherapy.

Addressing bone quality and bone density after renal transplantation: A prospective evaluation of the evolution of trabecular bone score and bone mineral density over the first 5 years following renal transplantation in Asian patients.

The evolution of trabecular bone score (TBS) and bone mineral density (BMD) over the first 5 years after renal transplantation was prospectively evaluated in 164 patients. Dual energy X-ray absorptiometry (DXA) scans were performed at 0, 6, 12, 24, and 60 months. Cumulative steroid dose, serum 25(OH)D, calcium, parathyroid hormone, and total ALP levels at these time points were checked. Incident fractures were identified from X-rays/vertebral fracture assessments. Mean (SD) age, TBS, and lumbar spine BMD at baseline were 47.11 (9.53), 1.424 (0.097), and 0.935 (0.183) gm/cm2 , respectively. Baseline TBS was lower in tertiary 1.38 (0.07) vs secondary hyperparathyroidism 1.43 (0.01) vs post-parathyroidectomy 1.46 (0.11); P = .035. Trabecular bone score and BMD significantly decreased from baseline->6 months, changes after that at consecutive time points were non-significant. 11% had incident fractures during the follow-up period, majority being metatarsal with no vertebral or hip fractures noted. This first prospective evaluation of TBS and BMD evolution at multiple time points over 5 years suggest that microarchitectural and bone density deteriorations post-renal transplantation stabilize after 6 months. Stabilization of these parameters could partially account for the absence of major fractures noted in this Asian population. Possible genetic and ethnic differences in fracture risk between Asian and Caucasian renal transplant patients have to be explored through large population-based studies.

Factors considered in end-of-life care decision making by health care professionals.

AIM: To explore the importance of factors influencing the end-of-life care decision making of health care professionals (HCPs) in Singapore. METHODS: This cross-sectional survey encompassed facets of patient, family, and HCP-related care considerations. In total, 187 questionnaires were distributed to physicians and nurses and had a response rate of 78.6%. RESULTS: The respondents rated patients' wishes (96.6%), their clinical symptoms (93.9%), and patients' beliefs (91.1%) very high. In all, 94.6% of the HCPs would respect a competent patient's wishes over the family's wishes when goals conflict. However, 59.9% of HCPs would abide by the family's wishes when the patient loses capacity even if the patient's previously expressed wishes are known. CONCLUSION: End-of-life care decision making by HCPs appears largely patient centered, although familial determination still wields significant influence with implications for advance care planning.

Should Patients and Family be Involved in "Do Not Resuscitate" Decisions? Views of Oncology and Palliative Care Doctors and Nurses.

BACKGROUND: "Do not resuscitate" (DNR) orders are put in place where cardiopulmonary resuscitation is inappropriate. However, it is unclear who should be involved in discussions and decisions around DNR orders. AIM: The aim was to determine the views of oncology and palliative care doctors and nurses on DNR orders. MATERIALS AND METHODS: A questionnaire survey was conducted on 146 doctors and nurses in oncology and palliative care working within a tertiary specialist cancer center in Singapore. RESULTS: Perceived care differences as a result of DNR determinations led to 50.7% of respondents reporting concerns that a DNR order would mean that the patient received a substandard level of care. On the matter of DNR discussions, majority thought that patients (78.8%) and the next of kin (78.1%) should be involved though with whom the ultimate decision lay differed. There was also a wide range of views on the most appropriate time to have a DNR discussion. CONCLUSIONS: From the viewpoint of oncology and palliative care healthcare professionals, patients should be involved at least in discussing if not in the determination of DNR orders, challenging the norm of familial determination in the Asian context. The varied responses highlight the complexity of decision making on issues relating to the end of life. Thus, it is important to take into account the innumerable bio-psychosocial, practical, and ethical factors that are involved within such deliberations.