Clinical and Surgical Applications of Large Language Models: A Systematic Review.

Background: Large language models (LLMs) represent a recent advancement in artificial intelligence with medical applications across various healthcare domains. The objective of this review is to highlight how LLMs can be utilized by clinicians and surgeons in their everyday practice. Methods: A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Six databases were searched to identify relevant articles. Eligibility criteria emphasized articles focused primarily on clinical and surgical applications of LLMs. Results: The literature search yielded 333 results, with 34 meeting eligibility criteria. All articles were from 2023. There were 14 original research articles, four letters, one interview, and 15 review articles. These articles covered a wide variety of medical specialties, including various surgical subspecialties. Conclusions: LLMs have the potential to enhance healthcare delivery. In clinical settings, LLMs can assist in diagnosis, treatment guidance, patient triage, physician knowledge augmentation, and administrative tasks. In surgical settings, LLMs can assist surgeons with documentation, surgical planning, and intraoperative guidance. However, addressing their limitations and concerns, particularly those related to accuracy and biases, is crucial. LLMs should be viewed as tools to complement, not replace, the expertise of healthcare professionals.

Artificial Intelligence in Postoperative Care: Assessing Large Language Models for Patient Recommendations in Plastic Surgery.

Since their release, the medical community has been actively exploring large language models' (LLMs) capabilities, which show promise in providing accurate medical knowledge. One potential application is as a patient resource. This study analyzes and compares the ability of the currently available LLMs, ChatGPT-3.5, GPT-4, and Gemini, to provide postoperative care recommendations to plastic surgery patients. We presented each model with 32 questions addressing common patient concerns after surgical cosmetic procedures and evaluated the medical accuracy, readability, understandability, and actionability of the models' responses. The three LLMs provided equally accurate information, with GPT-3.5 averaging the highest on the Likert scale (LS) (4.18 ± 0.93) (p = 0.849), while Gemini provided significantly more readable (p = 0.001) and understandable responses (p = 0.014; p = 0.001). There was no difference in the actionability of the models' responses (p = 0.830). Although LLMs have shown their potential as adjunctive tools in postoperative patient care, further refinement and research are imperative to enable their evolution into comprehensive standalone resources.

Large Language Models for Intraoperative Decision Support in Plastic Surgery: A Comparison between ChatGPT-4 and Gemini.

Background and Objectives: Large language models (LLMs) are emerging as valuable tools in plastic surgery, potentially reducing surgeons' cognitive loads and improving patients' outcomes. This study aimed to assess and compare the current state of the two most common and readily available LLMs, Open AI's ChatGPT-4 and Google's Gemini Pro (1.0 Pro), in providing intraoperative decision support in plastic and reconstructive surgery procedures. Materials and Methods: We presented each LLM with 32 independent intraoperative scenarios spanning 5 procedures. We utilized a 5-point and a 3-point Likert scale for medical accuracy and relevance, respectively. We determined the readability of the responses using the Flesch-Kincaid Grade Level (FKGL) and Flesch Reading Ease (FRE) score. Additionally, we measured the models' response time. We compared the performance using the Mann-Whitney U test and Student's t-test. Results: ChatGPT-4 significantly outperformed Gemini in providing accurate (3.59 ± 0.84 vs. 3.13 ± 0.83, p-value = 0.022) and relevant (2.28 ± 0.77 vs. 1.88 ± 0.83, p-value = 0.032) responses. Alternatively, Gemini provided more concise and readable responses, with an average FKGL (12.80 ± 1.56) significantly lower than ChatGPT-4's (15.00 ± 1.89) (p < 0.0001). However, there was no difference in the FRE scores (p = 0.174). Moreover, Gemini's average response time was significantly faster (8.15 ± 1.42 s) than ChatGPT'-4's (13.70 ± 2.87 s) (p < 0.0001). Conclusions: Although ChatGPT-4 provided more accurate and relevant responses, both models demonstrated potential as intraoperative tools. Nevertheless, their performance inconsistency across the different procedures underscores the need for further training and optimization to ensure their reliability as intraoperative decision-support tools.

Comparative Analysis of Large Language Models in Emergency Plastic Surgery Decision-Making: The Role of Physical Exam Data.

In the U.S., diagnostic errors are common across various healthcare settings due to factors like complex procedures and multiple healthcare providers, often exacerbated by inadequate initial evaluations. This study explores the role of Large Language Models (LLMs), specifically OpenAI's ChatGPT-4 and Google Gemini, in improving emergency decision-making in plastic and reconstructive surgery by evaluating their effectiveness both with and without physical examination data. Thirty medical vignettes covering emergency conditions such as fractures and nerve injuries were used to assess the diagnostic and management responses of the models. These responses were evaluated by medical professionals against established clinical guidelines, using statistical analyses including the Wilcoxon rank-sum test. Results showed that ChatGPT-4 consistently outperformed Gemini in both diagnosis and management, irrespective of the presence of physical examination data, though no significant differences were noted within each model's performance across different data scenarios. Conclusively, while ChatGPT-4 demonstrates superior accuracy and management capabilities, the addition of physical examination data, though enhancing response detail, did not significantly surpass traditional medical resources. This underscores the utility of AI in supporting clinical decision-making, particularly in scenarios with limited data, suggesting its role as a complement to, rather than a replacement for, comprehensive clinical evaluation and expertise.

Artificial Intelligence Support for Informal Patient Caregivers: A Systematic Review.

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.

Comparative Analysis of Artificial Intelligence Virtual Assistant and Large Language Models in Post-Operative Care.

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.

AI in Hand Surgery: Assessing Large Language Models in the Classification and Management of Hand Injuries.

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.

Artificial-Intelligence-Based Clinical Decision Support Systems in Primary Care: A Scoping Review of Current Clinical Implementations.

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.

Paper Tape May Improve Scar Aesthetics and Prevent Wound Closure Complications.

There is uncertainty whether postoperative application of paper tape (PT) improves scar aesthetics and reduces wound closure complications. This study aimed to review and assess the quality of applicable findings from studies investigating PT's efficacy. We queried PubMed and SCOPUS using the search terms "(("paper tape") AND (wound OR closure OR heal* OR complication OR skin OR prevent* OR scar*))." We excluded articles that were duplicates, basic science, or not clinically relevant. We assessed the level of evidence for each article using the American Society of Plastic Surgeons (ASPS) Rating Levels of Evidence and Grading Recommendations for Therapeutic Studies, ranging from I (highest) to V (lowest). Of 186 publications reviewed, we included eight studies in the literature review. Five of these studies reported statistically significant positive outcomes on scar aesthetics and wound closure associated with using PT. Using the ASPS rating system, we found that two studies were Level I, three studies were Level II, two studies were Level IV, and one study was Level V. Notably, heterogeneity in the study designs limited outcome comparison. The data from the studies included in this literature review support using PT to optimize scar and wound management. The lack of higher levels of evidence, however, suggests the need for additional randomized controlled trials to rigorously evaluate patient outcomes when using PT compared with other forms of adhesive dressings.

Evidence and Molecular Characterization of Multidrug Resistant Staphylococcus aureus Isolated From Equines in Pakistan.

The purpose of the current study was to investigate the nasal colonization and drug resistance profile of Staphylococcus aureus, methicillin-resistant S. aureus (MRSA), and vancomycin-resistant S. aureus (VRSA) in donkeys (n =63), mules (n = 42), and horses (n = 98). MRSA and VRSA were confirmed based on phenotypic and molecular methods, followed by phylogenetic analysis. Furthermore, the association of various animal and management-based risk factors with S. aureus colonization was also evaluated. The presence of nuc gene on polymerase chain reaction showed an overall prevalence of 42.86% of S. aureus in equines. Based on Kirby-Bauer disc diffusion test, 26.44% of isolates showed resistance to vancomycin. Further, mecA and vanB genes were targeted which showed an overall 14.94% and 13.79% prevalence of methicillin and vancomycin-resistant isolates, respectively. The phylogenetic analysis revealed a significant variation of the study isolates with each other and with already reported sequences of mecA and vanB genes. Risk factor analysis revealed that raising purpose (P = .011), work intensity (P < .001), stocking density (P = .006), presence of other livestock animals in surroundings (P = .043), and common drinking water source (P = .023) as significant. Antimicrobial susceptibility testing of MRSA and VRSA isolates showed high resistance to various commonly used antibiotics. Furthermore, all the tested isolates showing resistance to three or more than three antibiotics were considered multiple drug-resistant. The current study manifests the molecular evidence of MRSA and VRSA isolated from equines in Pakistan which will help to address the emerging issue of multidrug resistance in S. aureus in equines and emphasizes the need for possible measures to tackle this issue.

Molecular Characterization, Purification, and Mode of Action of Enterocin KAE01 from Lactic Acid Bacteria and Its In Silico Analysis against MDR/ESBL Pseudomonas aeruginosa.

Bacteriocins are gaining immense importance in therapeutics since they show significant antibacterial potential. This study reports the bacteriocin KAE01 from Enterococcus faecium, along with its characterization, molecular modeling, and antibacterial potency, by targeting the matrix protein of Pseudomonas aeruginosa. The bacteriocin was purified by using ammonium sulfate precipitation and fast protein liquid chromatography (FPLC), and its molecular weight was estimated as 55 kDa by means of SDS-PAGE. The bacteriocin was found to show stability in a wide range of pH values (2.0-10.0) and temperatures (100 °C for 1 h and 121 °C for 15 min). Antimicrobial screening of the purified peptide against different strains of P. aeruginosa showed its significant antibacterial potential. Scanning electron microscopy of bacteriocin-induced bacterial cultures revealed significant changes in the cellular morphology of the pathogens. In silico molecular modeling of KAE01, followed by molecular docking of the matrix protein (qSA) of P. aeruginosa and KAE01, supported the antibacterial potency and SEM findings of this study.

Arbuscular mycorrhizal fungi mitigate Fe deficiency symptoms in sorghum through phytosiderophore-mediated Fe mobilization and restoration of redox status.

Sustainable management of iron (Fe) deficiency through the microbial association is highly desirable to ensure crop yield. This study elucidates whether and how arbuscular mycorrhizal fungi (AMF) ameliorate Fe deficiency symptoms in sorghum. AMF inoculation showed a significant improvement in plant biomass, chlorophyll score, Fv/Fm (quantum efficiency of photosystem II), and Pi_ABS (photosynthesis performance index), suggesting its potentiality to diminish Fe deficiency symptoms in sorghum. This AMF-driven prevention of Fe deficiency was further supported by the improvement of biochemical stress indicators, such as cell death, electrolyte leakage, hydrogen peroxide, and superoxide anion. In this study, AMF showed a significant increase in phytosiderophore (PS) release as well as Fe and S concentrations in sorghum under Fe deficiency. Quantitative real-time PCR analysis demonstrated the consistent upregulation of SbDMAS2 (deoxymugineic acid synthase 2), SbNAS2 (nicotianamine synthase 2), and SbYS1 (Fe-phytosiderophore transporter yellow stripe) in roots due to AMF with Fe deficiency. It suggests that the enhancement of Fe due to AMF is related to the mobilization of Fe(III)-PS in the rhizosphere supported by the long-distance transport of Fe by SbYS1 transporter in sorghum. Our study further showed that the elevation of S mainly in the presence of AMF possibly enhances the S-containing antioxidant metabolites (Met, Cys, and GSH) as well as enzymes (CAT, SOD, and GR) to counteract H2O2 and O2- for the restoration of redox status in Fe-deprived sorghum. Moreover, S possibly participates in Strategy II responses revealing its crucial role as a signaling molecule for Fe homeostasis in sorghum.

Long-standing Sporadic Pancreatic Insulinoma: Report of a Rare Case.

Insulinomas are rare, functional pancreatic neuroendocrine tumors arising from the pancreatic multipotent stem cells or neuroendocrine islet, occurring with a higher proportion in females. Majority of insulinomas have a sporadic etiology; however, only 5%-10% develop as a part of multiple endocrine neoplasm type 1 syndrome. They usually present with symptoms of hypoglycemia including disturbance in orientation, tremors, diaphoresis, altered mental state, seizures and visual changes among others. The diagnosis is based on appreciation of the classic Whipple triad, i.e. neuroglycopenic symptoms and sympathetic drive along with low serum glucose levels (<50 mg/dL) and a complete reversibility of these symptoms with prompt administration of glucose. The gold standard treatment for insulinoma involves complete surgical excision (i.e. enucleation), which is curative in 90% of the patients. Health care physicians should have a high index of suspicion for this tumor in patients presenting with neurological and sympathetic symptoms, particularly if they are resolved after eating. Here, we report the case of a 48-year-old female with the history of multiple episodes of hypoglycemic symptoms for the past two years which improved on glucose intake. Furthermore, we also summarized the discussion regarding diagnosis and management of pancreatic insulinoma.

Health related quality of life of home dwelling vs. nursing facility dwelling elderly - A cross-sectional study from Karachi, Pakistan.

With the elderly population increasing in numbers, their demand of adequate medical and psychological care is also rising up. The key goal of promoting physical and mental health in elderly is maintenance of adequate health-related quality of life (QOL). A cross-sectional, descriptive study was conducted from December 2016 to February 2017 among 100 elderly living in nursing facilities and 100 in homes. Older people's quality of Life Questionnaire (OPQOL-35) was utilized to assess their QOL. In the nursing facility dwelling, 17% elderly reported good QOL with highest standardized score in "home and neighbourhood" and lowest in "health" domain. Of the home dwelling elderly, 74% reported good QOL with highest standardized score in "psychological and emotional wellbeing" and lowest in "health" domain.

Pheochromocytoma - An incidental finding in a child with acute appendicitis.

Pheochromocytoma, a rare tumour, arises mainly in the adrenal gland. It consists of chromaffin cells or sympathetic para-ganglia if extra-adrenal. It is an occurrence of rare nature with an incidence of two to eight cases per million annually. Incidence of paediatric pheochromocytoma is estimated at 0.11 benign and 0.02 malignant pheochromocytomas per million children. Children with it present with sustained hypertension in contrast to the adult triad of tachycardia, headache, and diaphoresis. We report a case in which the patient initially presented with right iliac fossa pain indicating appendicitis but later when evaluated and assessed, pheochromocytoma was diagnosed as well. The incidental nature of the finding, keeping in mind the rare occurrence makes the outcome interesting and intriguing at the same time.

Post-tuberculosis Aspergilloma in Undiagnosed Tetralogy of Fallot.

Tetralogy of Fallot (TOF) is the most common congenital heart disease (CHD) with an incidence of four in every 1000 live births in Pakistan. Classically, these children present with central cyanosis in early life; however, milder defects may remain asymptomatic for months or even years. We report a malnourished and anemic teenage male, who was admitted with shortness of breath, hemoptysis, fever, palpitations, and weight loss. On examination, vitals were stable, except for oxygen saturation, which was 84% on pulse-oximeter. Bilateral basal coarse crepitations were present on respiratory examination with a markedly reduced air entry in the right upper zone. A 2-3/6 systolic ejection murmur was appreciated on cardiac examination. The chest X-ray was consistent with a collapsed right upper lobe with fibrosis. Echocardiography was consistent with findings of TOF. Based on sputum for acid-fast bacilli (AFB smear) and GeneXpert (Cepheid Inc., Sunnyvale, California, US) Mycobacterium tuberculosis/resistance to rifampin (MTB/RIF), the patient was diagnosed with multi-drug resistant pulmonary tuberculosis (MDR-PTB). However, when the patient didn't improve with anti-tuberculous therapy, a computed tomography (CT) scan chest was done, which raised a suspicion of aspergilloma. The culture and cytology of bronchoalveolar lavage (BAL) were done, which confirmed pulmonary aspergilloma. Undiagnosed congenital heart diseases are rare in adults. Pulmonary TB is rarely reported in right-to-left shunts; however, clinicians should maintain a suspicion of this correlation.