Citations

In postoperative care, patient education and follow-up are pivotal for enhancing the quality of care and satisfaction. Artificial intelligence virtual assistants (AIVA) and large language models (LLMs) like Google BARD and ChatGPT-4 offer avenues for addressing patient queries using natural language processing (NLP) techniques. However, the accuracy and appropriateness of the information vary across these platforms, necessitating a comparative study to evaluate their efficacy in this domain. We conducted a study comparing AIVA (using Google Dialogflow) with ChatGPT-4 and Google BARD, assessing the accuracy, knowledge gap, and response appropriateness. AIVA demonstrated superior performance, with significantly higher accuracy (mean: 0.9) and lower knowledge gap (mean: 0.1) compared to BARD and ChatGPT-4. Additionally, AIVA’s responses received higher Likert scores for appropriateness. Our findings suggest that specialized AI tools like AIVA are more effective in delivering precise and contextually relevant information for postoperative care compared to general-purpose LLMs. While ChatGPT-4 shows promise, its performance varies, particularly in verbal interactions. This underscores the importance of tailored AI solutions in healthcare, where accuracy and clarity are paramount. Our study highlights the necessity for further research and the development of customized AI solutions to address specific medical contexts and improve patient outcomes.

This study aims to explore how artificial intelligence can help ease the burden on caregivers, filling a gap in current research and healthcare practices due to the growing challenge of an aging population and increased reliance on informal caregivers. We conducted a search with Google Scholar, PubMed, Scopus, IEEE Xplore, and Web of Science, focusing on AI and caregiving. Our inclusion criteria were studies where AI supports informal caregivers, excluding those solely for data collection. Adhering to PRISMA 2020 guidelines, we eliminated duplicates and screened for relevance. From 947 initially identified articles, 10 met our criteria, focusing on AI’s role in aiding informal caregivers. These studies, conducted between 2012 and 2023, were globally distributed, with 80% employing machine learning. Validation methods varied, with Hold-Out being the most frequent. Metrics across studies revealed accuracies ranging from 71.60% to 99.33%. Specific methods, like SCUT in conjunction with NNs and LibSVM, showcased accuracy between 93.42% and 95.36% as well as F-measures spanning 93.30% to 95.41%. AUC values indicated model performance variability, ranging from 0.50 to 0.85 in select models. Our review highlights AI’s role in aiding informal caregivers, showing promising results despite different approaches. AI tools provide smart, adaptive support, improving caregivers’ effectiveness and well-being.

Background: OpenAI’s ChatGPT (San Francisco, CA, USA) and Google’s Gemini (Mountain View, CA, USA) are two large language models that show promise in improving and expediting medical decision making in hand surgery. Evaluating the applications of these models within the field of hand surgery is warranted. This study aims to evaluate ChatGPT-4 and Gemini in classifying hand injuries and recommending treatment. Methods: Gemini and ChatGPT were given 68 fictionalized clinical vignettes of hand injuries twice. The models were asked to use a specific classification system and recommend surgical or nonsurgical treatment. Classifications were scored based on correctness. Results were analyzed using descriptive statistics, a paired two-tailed t-test, and sensitivity testing. Results: Gemini, correctly classifying 70.6% hand injuries, demonstrated superior classification ability over ChatGPT (mean score 1.46 vs. 0.87, p-value < 0.001). For management, ChatGPT demonstrated higher sensitivity in recommending surgical intervention compared to Gemini (98.0% vs. 88.8%), but lower specificity (68.4% vs. 94.7%). When compared to ChatGPT, Gemini demonstrated greater response replicability. Conclusions: Large language models like ChatGPT and Gemini show promise in assisting medical decision making, particularly in hand surgery, with Gemini generally outperforming ChatGPT. These findings emphasize the importance of considering the strengths and limitations of different models when integrating them into clinical practice.

Introduction: As large language models receive greater attention in medical research, the investigation of ethical considerations is warranted. This review aims to explore surgery literature to identify ethical concerns surrounding these artificial intelligence models and evaluate how autonomy, beneficence, nonmaleficence, and justice are represented within these ethical discussions to provide insights in order to guide further research and practice. Methods: A systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Five electronic databases were searched in October 2023. Eligible studies included surgery-related articles that focused on large language models and contained adequate ethical discussion. Study details, including specialty and ethical concerns, were collected. Results: The literature search yielded 1179 articles, with 53 meeting the inclusion criteria. Plastic surgery, orthopedic surgery, and neurosurgery were the most represented surgical specialties. Autonomy was the most explicitly cited ethical principle. The most frequently discussed ethical concern was accuracy (n = 45, 84.9%), followed by bias, patient confidentiality, and responsibility. Conclusion: The ethical implications of using large language models in surgery are complex and evolving. The integration of these models into surgery necessitates continuous ethical discourse to ensure responsible and ethical use, balancing technological advancement with human dignity and safety.

Abstract Clonal cytopenia of undetermined significance (CCUS) is defined by a myeloid driver mutation in the context of otherwise unexplained cytopenia. CCUS has an inherent risk of progressing to myeloid neoplasm. However, it is unknown how exposure to previous cytotoxic therapy may impact the risk of progression and survival. We stratified patients with CCUS by prior exposure to DNA-damaging therapy. Of 151 patients, 46 (30%) had received cytotoxic therapy and were classified as therapy-related CCUS (t-CCUS), whereas 105 (70%) had de novo CCUS. A lower proportion of t-CCUS had hypercellular marrows (17.8% vs 44.8%, P = .002) but had higher median bone marrow blast percentages. After a median follow-up of 2.2 years, t-CCUS had significantly shorter progression-free survival (PFS, 1.8 vs 6.3 years; hazard ratio [HR], 2.1; P = .007) and median overall survival (OS; 3.6 years vs not reached; HR, 2.3; P = .007) compared with CCUS. Univariable and multivariable time-to-event analyses showed that exposure to cytotoxic therapy independently accounted for inferior PFS and OS. Despite the similarities in clinical presentation between CCUS and t-CCUS, we show that exposure to prior cytotoxic therapies was an independent risk factor for inferior outcomes. This suggests that t-CCUS represents a unique clinical entity that needs more stringent monitoring or earlier intervention strategies.

Primary Care Physicians (PCPs) are the first point of contact in healthcare. Because PCPs face the challenge of managing diverse patient populations while maintaining up-to-date medical knowledge and updated health records, this study explores the current outcomes and effectiveness of implementing Artificial Intelligence-based Clinical Decision Support Systems (AI-CDSSs) in Primary Healthcare (PHC). Following the PRISMA-ScR guidelines, we systematically searched five databases, PubMed, Scopus, CINAHL, IEEE, and Google Scholar, and manually searched related articles. Only CDSSs powered by AI targeted to physicians and tested in real clinical PHC settings were included. From a total of 421 articles, 6 met our criteria. We found AI-CDSSs from the US, Netherlands, Spain, and China whose primary tasks included diagnosis support, management and treatment recommendations, and complication prediction. Secondary objectives included lessening physician work burden and reducing healthcare costs. While promising, the outcomes were hindered by physicians’ perceptions and cultural settings. This study underscores the potential of AI-CDSSs in improving clinical management, patient satisfaction, and safety while reducing physician workload. However, further work is needed to explore the broad spectrum of applications that the new AI-CDSSs have in several PHC real clinical settings and measure their clinical outcomes.

Eosinophilic granulomatosis with polyangiitis (EGPA) also referred to as Churg-Strauss syndrome is a rare vasculitis of the small to medium vessels. We present a rare case of acute coronary artery dissection brought on by EGPA, which generally has a poor prognosis. A 41-year-old male with history of bronchial asthma presented to the emergency room with a 2-week history of dyspnea, cough with clear phlegm, and fever. For the past eight months he had experienced episodes with similar symptoms relieved by steroids. CT chest showed bilateral upper lobe patchy opacities with extensive workup for infectious etiology being negative. He had peripheral eosinophilia with sinusitis. He had acute coronary syndrome and Coronary angiogram showed Right coronary artery dissection. After making a diagnosis of EGPA based on American college of Rheumatology criteria, he was successfully treated with high dose immunosuppression. Coronary artery dissection is a fatal and uncommon complication of EGPA which is usually diagnosed postmortem. Early recognition of this condition ante mortem and aggressive treatment can be lifesaving as demonstrated in our case.

Background and objectives: The incidence of morbidity and mortality in patients with type 2 diabetes mellitus is substantially correlated with cardiovascular disease and chronic kidney disease. The current guidelines recommend the use of renin-angiotensin system blockers, but recent studies probed into the effects of finerenone to mitigate the risk of cardiorenal events. This meta-analysis was performed to demonstrate the effects of finerenone on cardiorenal events, comprising cardiovascular mortality, heart failure, change in estimated glomerular filtration rate, and serum potassium levels. Methods: After screening with our eligibility criteria, 350 articles were identified with an initial literature search on multiple databases, including PubMed, Science Direct, and Cochrane Central. Seven randomized controlled trials with a total of 15 462 patients (n=8487 in the finerenone group; n=6975 in the control group) were included. Results: Patients receiving finerenone were at a reduced risk for cardiovascular mortality [HR: 0.84 (0.74, 0.95)], heart failure [OR: 0.79 (0.68, 0.92)], decrease in estimated glomerular filtration rate by 40% [OR: 0.82 (0.74, 0.91)] and by 57% [OR: 0.70 (0.59, 0.82)]; and a higher incidence of moderate hyperkalemia [OR: 2.25 (1.78, 2.84)]. Conclusion: Finerenone, owing to its better mineralocorticoid affinity, and a much lower risk of adverse effects, promises to be a much better alternative than other renin-angiotensin system blockers available for the treatment of chronic kidney disease patients with type 2 diabetes. Further trials should be conducted to provide more definitive evidence to assess the safety and efficacy of finerenone compared to spironolactone and eplerenone.

TPS3641 Background: Patients with mismatch repair proficient (pMMR) BRAF V600E mutant high-risk stage II (T4) or stage III colon cancer have a substantial risk of recurrence despite standard adjuvant therapy. In patients with metastatic BRAF V600E mutant colorectal cancer, the combination of the RAF inhibitor encorafenib and the EGFR inhibitor cetuximab has been shown to improve overall and progression-free survival compared to standard therapy after at least one prior line of therapy. This study will evaluate if this combination improves disease-free survival (DFS) in patients with resected BRAF V600E mutant pMMR/microsatellite stable (MSS) high-risk stage II (T4) or stage III colon cancer after standard adjuvant therapy. Methods: The study has a seamless phase II/III design, enrolling a maximum of 394 patients. BRAF mutation status can be determined locally or submitted for central testing in trial pre-screening. Eligible patients will be randomized 1:1 to usual surveillance versus 6 months of treatment with encorafenib (300mg oral daily) plus cetuximab (500mg/m2 intravenous every 14 days). Stratification factors are adjuvant chemotherapy regimen (FOLFOX versus CAPOX), duration of adjuvant therapy (3 months versus > 3 months), tumor stage (T4N0 versus T1-3N1 versus T4N1/TanyN2), and ctDNA marker status (detectable versus undetectable) at randomization. Adjuvant therapy must be completed at most 8 weeks prior to registration. For the phase II component, in the ctDNA detectable cohort, the primary endpoint will be ctDNA clearance rate at 6 months, and, in the ctDNA undetectable cohort, the primary endpoint will be 6-month ctDNA recurrence-free survival, where events consist of death, recurrence, or ctDNA positivity. The primary endpoint of the phase III component is DFS, and secondary endpoints are overall survival, adverse events, and alternative DFS calculated from the date of primary resection, rather than date of study randomization. Patient reported symptoms (PRO-CTCAE) will be collected and analyzed as an exploratory endpoint, and serial blood banking will support future correlative studies. The trial will proceed to the phase III portion if either of the two endpoints in the phase II cohorts is statistically superior in patients receiving encorafenib plus cetuximab. The phase III study sample size will provide 80% power at a one-sided α of 0.05 to detect an approximately 10% improvement in the three-year DFS rate, assuming 68% in the control arm. Two interim analyses will be performed for DFS endpoint. Support: U10CA180821, U10CA180882; https://acknowledgments.alliancefound.org . U10CA180820 (ECOG-ACRIN); U10CA180868 (NRG); U10CA180888 (SWOG); Pfizer, Eli Lilly; Clinicaltrials.gov ID: NCT05710406. Clinical trial information: NCT05710406 .