Search

Abstract Background The field of Artificial Intelligence (AI) holds transformative potential in medicine. However, the lack of universal reporting guidelines poses challenges in ensuring the validity and reproducibility of published research studies in this field. Methods Based on a systematic review of academic publications and reporting standards demanded by both international consortia and regulatory stakeholders as well as leading journals in the fields of medicine and medical informatics, 26 reporting guidelines published between 2009 and 2023 were included in this analysis. Guidelines were stratified by breadth (general or specific to medical fields), underlying consensus quality, and target research phase (preclinical, translational, clinical) and subsequently analyzed regarding the overlap and variations in guideline items. Results AI reporting guidelines for medical research vary with respect to the quality of the underlying consensus process, breadth, and target research phase. Some guideline items such as reporting of study design and model performance recur across guidelines, whereas other items are specific to particular fields and research stages. Conclusions Our analysis highlights the importance of reporting guidelines in clinical AI research and underscores the need for common standards that address the identified variations and gaps in current guidelines. Overall, this comprehensive overview could help researchers and public stakeholders reinforce quality standards for increased reliability, reproducibility, clinical validity, and public trust in AI research in healthcare. This could facilitate the safe, effective, and ethical translation of AI methods into clinical applications that will ultimately improve patient outcomes.

Abstract Deep Learning (DL) can predict biomarkers from cancer histopathology. Several clinically approved applications use this technology. Most approaches, however, predict categorical labels, whereas biomarkers are often continuous measurements. We hypothesize that regression-based DL outperforms classification-based DL. Therefore, we develop and evaluate a self-supervised attention-based weakly supervised regression method that predicts continuous biomarkers directly from 11,671 images of patients across nine cancer types. We test our method for multiple clinically and biologically relevant biomarkers: homologous recombination deficiency score, a clinically used pan-cancer biomarker, as well as markers of key biological processes in the tumor microenvironment. Using regression significantly enhances the accuracy of biomarker prediction, while also improving the predictions’ correspondence to regions of known clinical relevance over classification. In a large cohort of colorectal cancer patients, regression-based prediction scores provide a higher prognostic value than classification-based scores. Our open-source regression approach offers a promising alternative for continuous biomarker analysis in computational pathology.

Abstract Large language models (LLMs) are artificial intelligence (AI) tools specifically trained to process and generate text. LLMs attracted substantial public attention after OpenAI’s ChatGPT was made publicly available in November 2022. LLMs can often answer questions, summarize, paraphrase and translate text on a level that is nearly indistinguishable from human capabilities. The possibility to actively interact with models like ChatGPT makes LLMs attractive tools in various fields, including medicine. While these models have the potential to democratize medical knowledge and facilitate access to healthcare, they could equally distribute misinformation and exacerbate scientific misconduct due to a lack of accountability and transparency. In this article, we provide a systematic and comprehensive overview of the potentials and limitations of LLMs in clinical practice, medical research and medical education.

Abstract Clinically relevant postoperative pancreatic fistula (CR-POPF) can significantly affect the treatment course and outcome in pancreatic cancer patients. Preoperative prediction of CR-POPF can aid the surgical decision-making process and lead to better perioperative management of patients. In this retrospective study of 108 pancreatic head resection patients, we present risk models for the prediction of CR-POPF that use combinations of preoperative computed tomography (CT)-based radiomic features, mesh-based volumes of annotated intra- and peripancreatic structures and preoperative clinical data. The risk signatures were evaluated and analysed in detail by visualising feature expression maps and by comparing significant features to the established CR-POPF risk measures. Out of the risk models that were developed in this study, the combined radiomic and clinical signature performed best with an average area under receiver operating characteristic curve (AUC) of 0.86 and a balanced accuracy score of 0.76 on validation data. The following pre-operative features showed significant correlation with outcome in this signature ( $$p < 0.05$$ p < 0.05 ) - texture and morphology of the healthy pancreatic segment, intensity volume histogram-based feature of the pancreatic duct segment, morphology of the combined segment, and BMI. The predictions of this pre-operative signature showed strong correlation (Spearman correlation co-efficient, $$\rho = 0.7$$ ρ = 0.7 ) with the intraoperative updated alternative fistula risk score (ua-FRS), which is the clinical gold standard for intraoperative CR-POPF risk stratification. These results indicate that the proposed combined radiomic and clinical signature developed solely based on preoperatively available clinical and routine imaging data can perform on par with the current state-of-the-art intraoperative models for CR-POPF risk stratification.

Measurement(s) Laparoscopic Surgery Technology Type(s) Laparoscopy Factor Type(s) Presence and location of anatomical structures within laparoscopic images Sample Characteristic - Organism Homo sapiens Sample Characteristic - Environment abdomen Sample Characteristic - Location abdominal cavity

Abstract Clinically relevant postoperative pancreatic fistula (CR-POPF) is a common severe surgical complication after pancreatic surgery. Current risk stratification systems mostly rely on intraoperatively assessed factors like manually determined gland texture or blood loss. We developed a preoperatively available image-based risk score predicting CR-POPF as a complication of pancreatic head resection. Frequency of CR-POPF and occurrence of salvage completion pancreatectomy during the hospital stay were associated with an intraoperative surgical (sFRS) and image-based preoperative CT-based (rFRS) fistula risk score, both considering pancreatic gland texture, pancreatic duct diameter and pathology, in 195 patients undergoing pancreatic head resection. Based on its association with fistula-related outcome, radiologically estimated pancreatic remnant volume was included in a preoperative (preFRS) score for POPF risk stratification. Intraoperatively assessed pancreatic duct diameter (p

PurposeClinical abundance of artificial intelligence has increased significantly in the last decade. This survey aims to provide an overview of the current state of knowledge and acceptance of AI applications among surgeons in Germany.MethodsA total of 357 surgeons from German university hospitals, academic teaching hospitals and private practices were contacted by e-mail and asked to participate in the anonymous survey.ResultsA total of 147 physicians completed the survey. The majority of respondents (n = 85, 52.8%) stated that they were familiar with AI applications in medicine. Personal knowledge was self-rated as average (n = 67, 41.6%) or rudimentary (n = 60, 37.3%) by the majority of participants. On the basis of various application scenarios, it became apparent that the respondents have different demands on AI applications in the area of “diagnosis confirmation” as compared to the area of “therapy decision.” For the latter category, the requirements in terms of the error level are significantly higher and more respondents view their application in medical practice rather critically. Accordingly, most of the participants hope that AI systems will primarily improve diagnosis confirmation, while they see their ethical and legal problems with regard to liability as the main obstacle to extensive clinical application.ConclusionGerman surgeons are in principle positively disposed toward AI applications. However, many surgeons see a deficit in their own knowledge and in the implementation of AI applications in their own professional environment. Accordingly, medical education programs targeting both medical students and healthcare professionals should convey basic knowledge about the development and clinical implementation process of AI applications in different medical fields, including surgery.

Background Ultra-endurance cyclists regularly report various extents of bodily decline during long-distance bicycle rides, including potential kidney function-related symptoms such as swelling of body parts and urine changes. This study aimed to assess the prevalence of these symptoms in a representative cohort of ultra-endurance cyclists and shed light on potential predictors related to the ride, the rider and the rider’s behavior. Methods Between November 26 and December 14, 2020, 1350 people participated in an online survey investigating potential kidney-related symptoms of ultra-distance cycling. Frequency and severity of edema-like (“swelling”) symptoms and perceived changes in urine output, concentration and quality were associated with ride-related factors, demographic parameters and rider behavior-related variables. Results A total of 919 participants met the predefined inclusion criteria. The majority (N = 603, 65.6%) stated that they suffered from at least one potential kidney function-related symptom, out of which 498 (54.2%) stated one or more edema-like (“swelling”) symptoms. In correlational and multiple regression analyses, female sex, intake of analgesics and drinking strategies correlated with swelling symptoms. Further analyses indicated that drinking due to thirst and/or drinking adapted to ambient sweating and temperature negatively correlated with swelling symptoms, whereas “drinking as much as possible” enhanced these. Intake of analgesics was moderately positively correlated with swelling symptoms. Conclusions According to our survey, edema-like symptoms occur in the majority of ultra-distance cyclists and female sex, drinking strategy and intake of analgesic drugs are major predictors thereof. Studies are needed to investigate the underlying pathophysiological processes of such symptoms.

BackgroundThe potential risk and subsequent impact of serious complications after pancreatic and colorectal surgery can be significantly reduced through early recognition, correct assessment, and timely initiation of appropriate therapy. Serious gaming (SG) is an innovative teaching method that combines play with knowledge acquisition, increased concentration, and quick decision-making and could therefore be used for clinically oriented education. ObjectiveThis study aims to develop a case-based SG platform for complication management in pancreatic and colorectal surgery, validate the application by comparing game courses of various professional groups in the health care sector, and test the acceptance of the developed platform in the context of clinical education by measuring levels of usability and applicability within the framework of a validity and usefulness analysis. MethodsIn this observational trial, a novel SG for management of postoperative complications was developed and prospectively validated in a cohort of 131 human caregivers with varying experience in abdominal surgery. A total of 6 realistic patient cases were implemented, representing common complications after pancreatic and colorectal surgery. Cases were developed and illustrated using anonymized images, data, and histories of postoperative patients. In the prospective section of this study, following a brief case presentation, participants were asked to triage the virtual patient, make an initial suspected diagnosis, and design a 3-step management plan, throughout which the results of selected diagnostic and therapeutic actions were presented. Participants’ proposed case management was compared to ideal case management according to clinical guidelines. Usability, applicability, validity, and acceptance of the application were assessed using the Trier Teaching Evaluation Inventory as part of a noncomparative analysis. In addition, a comparative analysis of conventional teaching and learning formats was carried out. ResultsA total of 131 cases were answered. Physicians selected more appropriate therapeutic measures than nonphysicians. In the Trier Teaching Evaluation Inventory, design, structure, relevance, timeliness, and interest promotion were predominantly rated positively. Most participants perceived the application to be superior to conventional lecture-based formats (training courses, lectures, and seminars) in terms of problem-solving skills (102/131, 77.9%), self-reflection (102/131, 77.9%), and usability and applicability (104/131, 79.4%). ConclusionsCase-based SG has educational potential for complication management in surgery and could thereby contribute to improvements in postoperative patient care.