Generalizability of machine learning models predicting 30-day unplanned readmission after primary total knee arthroplasty using a nationally representative database.

Unplanned readmission after primary total knee arthroplasty (TKA) costs an average of US $39,000 per episode and negatively impacts patient outcomes. Although predictive machine learning (ML) models show promise for risk stratification in specific populations, existing studies do not address model generalizability. This study aimed to establish the generalizability of previous institutionally developed ML models to predict 30-day readmission following primary TKA using a national database. Data from 424,354 patients from the ACS-NSQIP database was used to develop and validate four ML models to predict 30-day readmission risk after primary TKA. Individual model performance was assessed and compared based on discrimination, accuracy, calibration, and clinical utility. Length of stay (> 2.5 days), body mass index (BMI) (> 33.21 kg/m2), and operation time (> 93 min) were important determinants of 30-day readmission. All ML models demonstrated equally good accuracy, calibration, and discriminatory ability (Brier score, ANN = RF = HGB = NEPLR = 0.03; ANN, slope = 0.90, intercept = - 0.11; RF, slope = 0.93, intercept = - 0.12; HGB, slope = 0.90, intercept = - 0.12; NEPLR, slope = 0.77, intercept = 0.01; AUCANN = AUCRF = AUCHGB = AUCNEPLR = 0.78). This study validates the generalizability of four previously developed ML algorithms in predicting readmission risk in patients undergoing TKA and offers surgeons an opportunity to reduce readmissions by optimizing discharge planning, BMI, and surgical efficiency.

Evaluating the Role of AI in Predicting the Success of Dental Implants Based on Preoperative CBCT Images: A Randomized Controlled Trial.

Background: Dental implant surgery has become a widely accepted method for replacing missing teeth. However, the success of dental implant procedures can be influenced by various factors, including the quality of preoperative planning and assessment. Cone beam computed tomography (CBCT) imaging provides valuable insights into a patient's oral anatomy, but accurately predicting implant success remains a challenge. Materials and Methods: In this randomized controlled trial (RCT), a cohort of 150 patients requiring dental implants was randomly divided into two groups: an artificial intelligence (AI)-assisted group and a traditional assessment group. Preoperative CBCT images of all patients were acquired and processed. The AI-assisted group utilized a machine learning model trained on historical data to assess implant success probability based on CBCT images, while the traditional assessment group relied on conventional methods and clinician expertise. Key parameters such as bone density, bone quality, and anatomical features were considered in the AI model. Results: After the completion of the study, the AI-assisted group demonstrated a significantly higher implant success rate, with 92% of implants successfully integrating into the bone compared to 78% in the traditional assessment group. The AI model showed an accuracy of 87% in predicting implant success, whereas traditional assessment methods achieved an accuracy of 71%. Additionally, the AI-assisted group had a lower rate of complications and required fewer postoperative interventions compared to the traditional assessment group. Conclusion: The AI-assisted approach significantly improved implant success rates and reduced complications, underscoring the importance of incorporating AI into the dental implant planning process.

Competitive organizational climate and artificial intelligence (AI) acceptance: the moderating role of leaders' power construal.

Introduction: The incorporation of Artificial Intelligence (AI) in organizations is pivotal to deal with work-related tasks and challenges effectively, yet little is known about the organizational factors that influence AI acceptance (i.e., employee favorable AI attitudes and AI use). To address this limitation in the literature and provide insight into the organizational antecedents influencing AI acceptance, this research investigated the relationship between competitive organizational climate and AI acceptance among employees. Moreover, given the critical role of a leader in employee attitude and behavior, we examined the moderating role of leaders' power construal as responsibility or as opportunity in this relationship. Methods: Study 1 was a three-wave field study among employees (N = 237, Mage = 38.28) working in various organizations in the UK. The study measured employees' perception of a competitive organizational climate at Time 1, leaders' power construal (as perceived by employees) at Time 2, and employee attitudes towards AI and their actual use of AI in the workplace at Times 2 and 3. Study 2 was a 2 (climate: highly competitive vs. low competitive) by 2 (power construal: responsibility vs. opportunity) experiment among employee participants (N = 150, Mage = 37.50). Results: Study 1 demonstrated a positive relationship between competitive climate and employee AI use over time. Furthermore, both studies revealed an interaction between competitive climate and leader's power construal in the prediction of employee AI acceptance: In Study 1, competitive climate was negatively related to AI acceptance over time when leaders construed power as opportunity. In Study 2 competitive climate was positively related to AI acceptance when leaders construed power as responsibility rather than as opportunity. Discussion: These results underscore the organizational factors that are required in order for employees to shape favorable attitudes towards AI and actually use AI at work. Importantly, this research expands the limited body of literature on AI integration in organizations.

Emerging Vanadium-Doped Cobalt Chloride Carbonate Hydroxide for Flexible Electrochromic Micro-Supercapacitor: Charged-State Prediction from RGB Input by ANN Model.

Multifunctional devices integrated with electrochromic and supercapacitance properties are fascinating because of their extensive usage in modern electronic applications. In this work, vanadium-doped cobalt chloride carbonate hydroxide hydrate nanostructures (V-C3H NSs) are successfully synthesized and show unique electrochromic and supercapacitor properties. The V-C3H NSs material exhibits a high specific capacitance of 1219.9 F g-1 at 1 mV s-1 with a capacitance retention of 100% over 30 000 CV cycles. The electrochromic performance of the V-C3H NSs material is confirmed through in situ spectroelectrochemical measurements, where the switching time, coloration efficiency (CE), and optical modulation (∆T) are found to be 15.7 and 18.8 s, 65.85 cm2 C-1 and 69%, respectively. A coupled multilayer artificial neural network (ANN) model is framed to predict potential and current from red (R), green (G), and blue (B) color values. The optimized V-C3H NSs are used as the active materials in the fabrication of flexible/wearable electrochromic micro-supercapacitor devices (FEMSDs) through a cost-effective mask-assisted vacuum filtration method. The fabricated FEMSD exhibits an areal capacitance of 47.15 mF cm-2 at 1 mV s-1 and offers a maximum areal energy and power density of 104.78 Wh cm-2 and 0.04 mW cm-2, respectively. This material's interesting energy storage and electrochromic properties are promising in multifunctional electrochromic energy storage applications.

Comparing ChatGPT's and surgeon's responses to thyroid-related questions from patients.

BACKGROUND: For some common thyroid-related conditions with high prevalence and long follow-up times, ChatGPT can be used to respond to common thyroid-related questions. In this cross-sectional study, we assessed the ability of ChatGPT (version GPT-4.0) to provide accurate, comprehensive, compassionate, and satisfactory responses to common thyroid-related questions. STUDY DESIGN: First, we obtained 28 thyroid-related questions from the Huayitong app, which together with the two interfering questions eventually formed 30 questions. Then, these questions were responded to by ChatGPT (on July 19, 2023), junior specialist and senior specialist (on July 20, 2023) separately. Finally, 26 patients and 11 thyroid surgeons evaluated those responses on four dimensions: accuracy, comprehensiveness, compassion, and satisfaction. RESULTS: Among the 30 questions and responses, ChatGPT's speed of response was faster than that of the junior specialist (8.69 [7.53-9.48] vs. 4.33 [4.05-4.60], P <.001) and senior specialist (8.69 [7.53-9.48] vs. 4.22 [3.36-4.76], P <.001). The word count of the ChatGPT's responses was greater than that of both junior specialist (341.50 [301.00-384.25] vs. 74.50 [51.75-84.75], P <0.001) and senior specialist (341.50 [301.00-384.25] vs. 104.00 [63.75-177.75], P <0.001). ChatGPT received higher scores than junior specialist and senior specialist in terms of accuracy, comprehensiveness, compassion and satisfaction in responding to common thyroid-related questions. CONCLUSIONS: ChatGPT performed better than junior specialist and senior specialist in answering common thyroid-related questions, but further research is needed to validate the logical ability of the ChatGPT for complex thyroid questions.

Use of artificial intelligence in breast surgery: a narrative review.

Background and Objective: We have witnessed tremendous advances in artificial intelligence (AI) technologies. Breast surgery, a subspecialty of general surgery, has notably benefited from AI technologies. This review aims to evaluate how AI has been integrated into breast surgery practices, to assess its effectiveness in improving surgical outcomes and operational efficiency, and to identify potential areas for future research and application. Methods: Two authors independently conducted a comprehensive search of PubMed, Google Scholar, EMBASE, and Cochrane CENTRAL databases from January 1, 1950, to September 4, 2023, employing keywords pertinent to AI in conjunction with breast surgery or cancer. The search focused on English language publications, where relevance was determined through meticulous screening of titles, abstracts, and full-texts, followed by an additional review of references within these articles. The review covered a range of studies illustrating the applications of AI in breast surgery encompassing lesion diagnosis to postoperative follow-up. Publications focusing specifically on breast reconstruction were excluded. Key Content and Findings: AI models have preoperative, intraoperative, and postoperative applications in the field of breast surgery. Using breast imaging scans and patient data, AI models have been designed to predict the risk of breast cancer and determine the need for breast cancer surgery. In addition, using breast imaging scans and histopathological slides, models were used for detecting, classifying, segmenting, grading, and staging breast tumors. Preoperative applications included patient education and the display of expected aesthetic outcomes. Models were also designed to provide intraoperative assistance for precise tumor resection and margin status assessment. As well, AI was used to predict postoperative complications, survival, and cancer recurrence. Conclusions: Extra research is required to move AI models from the experimental stage to actual implementation in healthcare. With the rapid evolution of AI, further applications are expected in the coming years including direct performance of breast surgery. Breast surgeons should be updated with the advances in AI applications in breast surgery to provide the best care for their patients.

Enhancing IEP Goal Development for Preschoolers with Autism: A Preliminary Study on ChatGPT Integration.

PURPOSE: The impact of well-crafted IEP goals on student outcomes is well-documented, but creating high-quality goals can be a challenging task for many special education teachers. This study aims to investigate potential effectiveness of using ChatGPT, an AI technology, in supporting development of high-quality, individualized IEP goals for preschool children with autism. METHODS: Thirty special education teachers working with preschool children with autism were randomly assigned to either the ChatGPT or control groups. Both groups received written guidelines on how to write SMART IEP goals, but only the ChatGPT group was given handout on how to use ChatGPT during IEP goal writing process. Quality of IEP goals written by the two groups was compared using a two-sample t-test, and categorization of goals by developmental domains was reported using frequency counts. RESULTS: Results indicate that using ChatGPT significantly improved the quality of IEP goals developed by special education teachers compared to those who did not use the technology. Teachers in the ChatGPT group had a higher proportion of goals targeting communication, social skills, motor/sensory, and self-care skills, while teachers in the control group had a higher proportion of goals targeting preacademic skills and behaviors. CONCLUSION: The potential of ChatGPT as an effective tool for supporting special education teachers in developing high-quality IEP goals suggests promising implications for improving outcomes for preschool children with autism. Its integration may offer valuable assistance in tailoring individualized goals to meet the diverse needs of students in special education settings.

Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records.

Background: Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods: A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results: Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions: Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.

An AI-based multiphase framework for improving the mechanical ventilation availability in emergency departments during respiratory disease seasons: a case study.

BACKGROUND: Shortages of mechanical ventilation have become a constant problem in Emergency Departments (EDs), thereby affecting the timely deployment of medical interventions that counteract the severe health complications experienced during respiratory disease seasons. It is then necessary to count on agile and robust methodological approaches predicting the expected demand loads to EDs while supporting the timely allocation of ventilators. In this paper, we propose an integration of Artificial Intelligence (AI) and Discrete-event Simulation (DES) to design effective interventions ensuring the high availability of ventilators for patients needing these devices. METHODS: First, we applied Random Forest (RF) to estimate the mechanical ventilation probability of respiratory-affected patients entering the emergency wards. Second, we introduced the RF predictions into a DES model to diagnose the response of EDs in terms of mechanical ventilator availability. Lately, we pretested two different interventions suggested by decision-makers to address the scarcity of this resource. A case study in a European hospital group was used to validate the proposed methodology. RESULTS: The number of patients in the training cohort was 734, while the test group comprised 315. The sensitivity of the AI model was 93.08% (95% confidence interval, [88.46 - 96.26%]), whilst the specificity was 85.45% [77.45 - 91.45%]. On the other hand, the positive and negative predictive values were 91.62% (86.75 - 95.13%) and 87.85% (80.12 - 93.36%). Also, the Receiver Operator Characteristic (ROC) curve plot was 95.00% (89.25 - 100%). Finally, the median waiting time for mechanical ventilation was decreased by 17.48% after implementing a new resource capacity strategy. CONCLUSIONS: Combining AI and DES helps healthcare decision-makers to elucidate interventions shortening the waiting times for mechanical ventilators in EDs during respiratory disease epidemics and pandemics.

A systematic review of robotic efficacy in coral reef monitoring techniques.

Coral reefs are home to a variety of species, and their preservation is a popular study area; however, monitoring them is a significant challenge, for which the use of robots offers a promising answer. The purpose of this study is to analyze the current techniques and tools employed in coral reef monitoring, with a focus on the role of robotics and its potential in transforming this sector. Using a systematic review methodology examining peer-reviewed literature across engineering and earth sciences from the Scopus database focusing on "robotics" and "coral reef" keywords, the article is divided into three sections: coral reef monitoring, robots in coral reef monitoring, and case studies. The initial findings indicated a variety of monitoring strategies, each with its own advantages and disadvantages. Case studies have also highlighted the global application of robotics in monitoring, emphasizing the challenges and opportunities unique to each context. Robotic interventions driven by artificial intelligence and machine learning have led to a new era in coral reef monitoring. Such developments not only improve monitoring but also support the conservation and restoration of these vulnerable ecosystems. Further research is required, particularly on robotic systems for monitoring coral nurseries and maximizing coral health in both indoor and open-sea settings.

Large language models as assistance for glaucoma surgical cases: a ChatGPT vs. Google Gemini comparison.

PURPOSE: The aim of this study was to define the capability of ChatGPT-4 and Google Gemini in analyzing detailed glaucoma case descriptions and suggesting an accurate surgical plan. METHODS: Retrospective analysis of 60 medical records of surgical glaucoma was divided into "ordinary" (n = 40) and "challenging" (n = 20) scenarios. Case descriptions were entered into ChatGPT and Bard's interfaces with the question "What kind of surgery would you perform?" and repeated three times to analyze the answers' consistency. After collecting the answers, we assessed the level of agreement with the unified opinion of three glaucoma surgeons. Moreover, we graded the quality of the responses with scores from 1 (poor quality) to 5 (excellent quality), according to the Global Quality Score (GQS) and compared the results. RESULTS: ChatGPT surgical choice was consistent with those of glaucoma specialists in 35/60 cases (58%), compared to 19/60 (32%) of Gemini (p = 0.0001). Gemini was not able to complete the task in 16 cases (27%). Trabeculectomy was the most frequent choice for both chatbots (53% and 50% for ChatGPT and Gemini, respectively). In "challenging" cases, ChatGPT agreed with specialists in 9/20 choices (45%), outperforming Google Gemini performances (4/20, 20%). Overall, GQS scores were 3.5 ± 1.2 and 2.1 ± 1.5 for ChatGPT and Gemini (p = 0.002). This difference was even more marked if focusing only on "challenging" cases (1.5 ± 1.4 vs. 3.0 ± 1.5, p = 0.001). CONCLUSION: ChatGPT-4 showed a good analysis performance for glaucoma surgical cases, either ordinary or challenging. On the other side, Google Gemini showed strong limitations in this setting, presenting high rates of unprecise or missed answers.

ChatGPT Performance on the American Shoulder and Elbow Surgeons Maintenance of Certification Exam.

BACKGROUND: While multiple studies have tested the ability of large language models (LLM), such as ChatGPT, to pass standardized medical exams at different levels of training, LLMs have never been tested on surgical sub-specialty examinations, such as the American Shoulder and Elbow Surgeons (ASES) Maintenance of Certification (MOC). The purpose of this study was to compare results of ChatGPT 3.5, GPT-4, and fellowship-trained surgeons on the 2023 American Shoulder and Elbow Surgeons (ASES) Maintenance of Certification (MOC) self-assessment exam. METHODS: ChatGPT 3.5 and GPT-4 were subjected to the same set of text-only questions from the ASES MOC exam, and GPT-4 was additionally subjected to image-based MOC exam questions. Question responses from both models were compared against the correct answers. Performance of both models was compared to corresponding average human performance on the same question subsets. One sided proportional z-test were utilized to analyze data. RESULTS: Humans performed significantly better than Chat GPT 3.5 on exclusively text-based questions (76.4% vs. 60.8%, p= .044). Humans also performed significantly better than GPT 4 on image-based questions (73.9% vs. 53.2%, p= .019). There was no significant difference between humans and GPT 4 in text-based questions (76.4% vs. 66.7%, p=0.136). Accounting for all questions, humans significantly outperformed GPT-4 (75.3% vs. 60.2%, p= .012). GPT-4 did not perform statistically significantly betterer than ChatGPT 3.5 on text-only questions (66.7% vs. 60.8%, p= .268). DISCUSSION: Although human performance was overall superior, ChatGPT demonstrated the capacity to analyze orthopedic information and answer specialty-specific questions on the ASES MOC exam for both text and image-based questions. With continued advancements in deep learning, large language models may someday rival exam performance of fellowship-trained surgeons.

Comparing the Performance of Popular Large Language Models on the National Board of Medical Examiners Sample Questions.

INTRODUCTION: Large language models (LLMs) have transformed various domains in medicine, aiding in complex tasks and clinical decision-making, with OpenAI's GPT-4, GPT-3.5, Google's Bard, and Anthropic's Claude among the most widely used. While GPT-4 has demonstrated superior performance in some studies, comprehensive comparisons among these models remain limited. Recognizing the significance of the National Board of Medical Examiners (NBME) exams in assessing the clinical knowledge of medical students, this study aims to compare the accuracy of popular LLMs on NBME clinical subject exam sample questions. METHODS: The questions used in this study were multiple-choice questions obtained from the official NBME website and are publicly available. Questions from the NBME subject exams in medicine, pediatrics, obstetrics and gynecology, clinical neurology, ambulatory care, family medicine, psychiatry, and surgery were used to query each LLM. The responses from GPT-4, GPT-3.5, Claude, and Bard were collected in October 2023. The response by each LLM was compared to the answer provided by the NBME and checked for accuracy. Statistical analysis was performed using one-way analysis of variance (ANOVA). RESULTS: A total of 163 questions were queried by each LLM. GPT-4 scored 163/163 (100%), GPT-3.5 scored 134/163 (82.2%), Bard scored 123/163 (75.5%), and Claude scored 138/163 (84.7%). The total performance of GPT-4 was statistically superior to that of GPT-3.5, Claude, and Bard by 17.8%, 15.3%, and 24.5%, respectively. The total performance of GPT-3.5, Claude, and Bard was not significantly different. GPT-4 significantly outperformed Bard in specific subjects, including medicine, pediatrics, family medicine, and ambulatory care, and GPT-3.5 in ambulatory care and family medicine. Across all LLMs, the surgery exam had the highest average score (18.25/20), while the family medicine exam had the lowest average score (3.75/5).  Conclusion: GPT-4's superior performance on NBME clinical subject exam sample questions underscores its potential in medical education and practice. While LLMs exhibit promise, discernment in their application is crucial, considering occasional inaccuracies. As technological advancements continue, regular reassessments and refinements are imperative to maintain their reliability and relevance in medicine.

Digital health and health equity: How digital health can address healthcare disparities and improve access to quality care in Africa.

The healthcare industry is constantly evolving to bridge the inequality gap and provide precision care to its diverse population. One of these approaches is the integration of digital health tools into healthcare delivery. Significant milestones such as reduced maternal mortality, rising and rapidly proliferating health tech start-ups, and the use of drones and smart devices for remote health service delivery, among others, have been reported. However, limited access to family planning, migration of health professionals, climate change, gender inequity, increased urbanization, and poor integration of private health firms into healthcare delivery rubrics continue to impair the attainment of universal health coverage and health equity. Health policy development for an integrated health system without stigma, addressing inequalities of all forms, should be implemented. Telehealth promotion, increased access to infrastructure, international collaborations, and investment in health interventions should be continuously advocated to upscale the current health landscape and achieve health equity.

Landscape analysis of available European data sources amenable for machine learning and recommendations on usability for rare diseases screening.

BACKGROUND: Patient registries and databases are essential tools for advancing clinical research in the area of rare diseases, as well as for enhancing patient care and healthcare planning. The primary aim of this study is a landscape analysis of available European data sources amenable to machine learning (ML) and their usability for Rare Diseases screening, in terms of findable, accessible, interoperable, reusable(FAIR), legal, and business considerations. Second, recommendations will be proposed to provide a better understanding of the health data ecosystem. METHODS: In the period of March 2022 to December 2022, a cross-sectional study using a semi-structured questionnaire was conducted among potential respondents, identified as main contact person of a health-related databases. The design of the self-completed questionnaire survey instrument was based on information drawn from relevant scientific publications, quantitative and qualitative research, and scoping review on challenges in mapping European rare disease (RD) databases. To determine database characteristics associated with the adherence to the FAIR principles, legal and business aspects of database management Bayesian models were fitted. RESULTS: In total, 330 unique replies were processed and analyzed, reflecting the same number of distinct databases (no duplicates included). In terms of geographical scope, we observed 24.2% (n = 80) national, 10.0% (n = 33) regional, 8.8% (n = 29) European, and 5.5% (n = 18) international registries coordinated in Europe. Over 80.0% (n = 269) of the databases were still active, with approximately 60.0% (n = 191) established after the year 2000 and 71.0% last collected new data in 2022. Regarding their geographical scope, European registries were associated with the highest overall FAIR adherence, while registries with regional and "other" geographical scope were ranked at the bottom of the list with the lowest proportion. Responders' willingness to share data as a contribution to the goals of the Screen4Care project was evaluated at the end of the survey. This question was completed by 108 respondents; however, only 18 of them (16.7%) expressed a direct willingness to contribute to the project by sharing their databases. Among them, an equal split between pro-bono and paid services was observed. CONCLUSIONS: The most important results of our study demonstrate not enough sufficient FAIR principles adherence and low willingness of the EU health databases to share patient information, combined with some legislation incapacities, resulting in barriers to the secondary use of data.

Web-accessible critical limits and critical values for urgent clinician notification.

OBJECTIVES: To survey the World Wide Web for critical limits/critical values, assess changes in quantitative low/high thresholds since 1990-93, streamline urgent notification practices, and promote global accessibility. METHODS: We identified Web-posted lists of critical limits/values at university hospitals. We compared 2023 to 1990-93 archived notification thresholds. RESULTS: We found critical notification lists for 26 university hospitals. Laboratory disciplines ranged widely (1-10). The median number of tests was 62 (range 21-116); several posted policies. The breadth of listings increased. Statistically significant differences in 2023 vs. 1990 critical limits were observed for blood gas (pO2, pCO2), chemistry (glucose, calcium, magnesium), and hematology (hemoglobin, platelets, PTT, WBC) tests, and for newborn glucose, potassium, pO2, and hematocrit. Twenty hospitals listed ionized calcium critical limits, which have not changed. Fourteen listed troponin (6), troponin I (3), hs-TnI (3), or troponin T (2). Qualitative critical values expanded across disciplines, encompassing anatomic/surgical pathology. Bioterrorism agents were listed frequently, as were contagious pathogens, although only three hospitals listed COVID-19. Only one notification list detailed point-of-care tests. Two children's hospital lists were Web-accessible. CONCLUSIONS: Urgent notifications should focus on life-threatening conditions. We recommend that hospital staff evaluate changes over the past three decades for clinical impact. Notification lists expanded, especially qualitative tests, suggesting that automation might improve efficiency. Sharing notification lists and policies on the Web will improve accessibility. If not dependent on the limited scope of secondary sources, artificial intelligence could enhance knowledge of urgent notification and critical care practices in the 21st Century.

Utilizing artificial intelligence in academic writing: an in-depth evaluation of a scientific review on fertility preservation written by ChatGPT-4.

PURPOSE: To evaluate the ability of ChatGPT-4 to generate a biomedical review article on fertility preservation. METHODS: ChatGPT-4 was prompted to create an outline for a review on fertility preservation in men and prepubertal boys. The outline provided by ChatGPT-4 was subsequently used to prompt ChatGPT-4 to write the different parts of the review and provide five references for each section. The different parts of the article and the references provided were combined to create a single scientific review that was evaluated by the authors, who are experts in fertility preservation. The experts assessed the article and the references for accuracy and checked for plagiarism using online tools. In addition, both experts independently scored the relevance, depth, and currentness of the ChatGPT-4's article using a scoring matrix ranging from 0 to 5 where higher scores indicate higher quality. RESULTS: ChatGPT-4 successfully generated a relevant scientific article with references. Among 27 statements needing citations, four were inaccurate. Of 25 references, 36% were accurate, 48% had correct titles but other errors, and 16% were completely fabricated. Plagiarism was minimal (mean = 3%). Experts rated the article's relevance highly (5/5) but gave lower scores for depth (2-3/5) and currentness (3/5). CONCLUSION: ChatGPT-4 can produce a scientific review on fertility preservation with minimal plagiarism. While precise in content, it showed factual and contextual inaccuracies and inconsistent reference reliability. These issues limit ChatGPT-4 as a sole tool for scientific writing but suggest its potential as an aid in the writing process.

Machine learning approach for ambient-light-corrected parameters and the Pupil Reactivity score in smartphone-based pupillometry.

Introduction: The pupillary light reflex (PLR) is the constriction of the pupil in response to light. The PLR in response to a pulse of light follows a complex waveform that can be characterized by several parameters. It is a sensitive marker of acute neurological deterioration, but is also sensitive to the background illumination in the environment in which it is measured. To detect a pathological change in the PLR, it is therefore necessary to separate the contributions of neuro-ophthalmic factors from ambient illumination. Illumination varies over several orders of magnitude and is difficult to control due to diurnal, seasonal, and location variations. Methods and results: We assessed the sensitivity of seven PLR parameters to differences in ambient light, using a smartphone-based pupillometer (AI Pupillometer, Solvemed Inc.). Nine subjects underwent 345 measurements in ambient conditions ranging from complete darkness (<5 lx) to bright lighting (≲10,000 lx). Lighting most strongly affected the initial pupil size, constriction amplitude, and velocity. Nonlinear models were fitted to find the correction function that maximally stabilized PLR parameters across different ambient light levels. Next, we demonstrated that the lighting-corrected parameters still discriminated reactive from unreactive pupils. Ten patients underwent PLR testing in an ophthalmology outpatient clinic setting following the administration of tropicamide eye drops, which rendered the pupils unreactive. The parameters corrected for lighting were combined as predictors in a machine learning model to produce a scalar value, the Pupil Reactivity (PuRe) score, which quantifies Pupil Reactivity on a scale 0-5 (0, non-reactive pupil; 0-3, abnormal/"sluggish" response; 3-5, normal/brisk response). The score discriminated unreactive pupils with 100% accuracy and was stable under changes in ambient illumination across four orders of magnitude. Discussion: This is the first time that a correction method has been proposed to effectively mitigate the confounding influence of ambient light on PLR measurements, which could improve the reliability of pupillometric parameters both in pre-hospital and inpatient care settings. In particular, the PuRe score offers a robust measure of Pupil Reactivity directly applicable to clinical practice. Importantly, the formulae behind the score are openly available for the benefit of the clinical research community.