Most clinical information is only available as free text. Large language models (LLMs) are increasingly applied to clinical data to streamline communication, enhance the accuracy of clinical documentation, and ultimately improve healthcare delivery. This study focuses on a corpus of anonymized clinical narratives in German. On the one hand it evaluates the use of ChatGPT for text cleaning, i.e., the automatic rephrasing of raw text into a more readable and standardized form, and on the other hand for retrieval-augmented generation (RAG). In both tasks, the final goal was medical concept normalization (MCN), i.e., the annotation of text segments with codes from a controlled vocabulary using natural language processing.We found that ChatGPT (GPT-4) significantly improves precision and recall compared to simple dictionary matching. For all scenarios, the importance of the underlying terminological basis was also demonstrated. Maximum F1 scores of 0.607, 0.735 and 0.754 (i.e, for top 1, 5 and 10 matches) were achieved through a pipeline including document cleaning, bi-encoder-based term matching based on a large domain dictionary linked to SNOMED CT, and finally re-ranking using RAG.

Patient care after kidney transplantation requires integration of complex information to make informed decisions on risk constellations. Many machine learning models have been developed for detecting patient outcomes in the past years. However, performance metrics alone do not determine practical utility. We present a newly developed clinical decision support system (CDSS) for detection of patients at risk for rejection and death-censored graft failure. The CDSS is based on clinical routine data including 1,516 kidney transplant recipients and more than 100,000 data points. In a reader study we compare the performance of physicians at a nephrology department with and without the CDSS. Internal validation shows AUC-ROC scores of 0.83 for rejection, and 0.95 for graft failure. The reader study shows that predictions by physicians converge toward the CDSS. However, performance does not improve (AUC–ROC; 0.6413 vs. 0.6314 for rejection; 0.8072 vs. 0.7778 for graft failure). Finally, the study shows that the CDSS detects partially different patients at risk compared to physicians. This indicates that the combination of both, medical professionals and a CDSS might help detect more patients at risk for graft failure. However, the question of how to integrate such a system efficiently into clinical practice remains open.

Introduction As healthcare is shifting from a paternalistic to a patient-centred approach, medical decision making becomes more collaborative involving patients, their support persons (SPs) and physicians. Implementing shared decision-making (SDM) into clinical practice can be challenging and becomes even more complex with the introduction of artificial intelligence (AI) as a potential actant in the communicative network. Although there is more empirical research on patients’ and physicians’ perceptions of AI, little is known about the impact of AI on SDM. This study will help to fill this gap. To the best of our knowledge, this is the first systematic empirical investigation to prospectively assess the views of patients, their SPs and physicians on how AI affects SDM in physician–patient communication after kidney transplantation. Using a transdisciplinary approach, this study will explore the role and impact of an AI-decision support system (DSS) designed to assist with medical decision making in the clinical encounter. Methods and analysis This is a plan to roll out a 2 year, longitudinal qualitative interview study in a German kidney transplant centre. Semi-structured interviews with patients, SPs and physicians will be conducted at baseline and in 3-, 6-, 12- and 24-month follow-up. A total of 50 patient–SP dyads and their treating physicians will be recruited at baseline. Assuming a dropout rate of 20% per year, it is anticipated that 30 patient–SP dyads will be included in the last follow-up with the aim of achieving data saturation. Interviews will be audio-recorded and transcribed verbatim. Transcripts will be analysed using framework analysis. Participants will be asked to report on their (a) communication experiences and preferences, (b) views on the influence of the AI-based DSS on the normative foundations of the use of AI in medical decision-making, focusing on agency along with trustworthiness, transparency and responsibility and (c) perceptions of the use of the AI-based DSS, as well as barriers and facilitators to its implementation into routine care. Ethics and dissemination Approval has been granted by the local ethics committee of Charité—Universitätsmedizin Berlin (EA1/177/23 on 08 August 2023). This research will be conducted in accordance with the principles of the Declaration of Helsinki (1996). The study findings will be used to develop communication guidance for physicians on how to introduce and sustainably implement AI-assisted SDM. The study results will also be used to develop lay language patient information on AI-assisted SDM. A broad dissemination strategy will help communicate the results of this research to a variety of target groups, including scientific and non-scientific audiences, to allow for a more informed discourse among different actors from policy, science and society on the role and impact of AI in physician–patient communication.

Background: Patients after kidney transplantation eventually face the risk of graft loss with the concomitant need for dialysis or retransplantation. Choosing the right kidney replacement therapy after graft loss is an important preference-sensitive decision for kidney transplant recipients. However, the rate of conversations about treatment options after kidney graft loss has been shown to be as low as 13% in previous studies. It is unknown whether the implementation of artificial intelligence (AI)–based risk prediction models can increase the number of conversations about treatment options after graft loss and how this might influence the associated shared decision-making (SDM). Objective: This study aims to explore the impact of AI-based risk prediction for the risk of graft loss on the frequency of conversations about the treatment options after graft loss, as well as the associated SDM process. Methods: This is a 2-year, prospective, randomized, 2-armed, parallel-group, single-center trial in a German kidney transplant center. All patients will receive the same routine post–kidney transplant care that usually includes follow-up visits every 3 months at the kidney transplant center. For patients in the intervention arm, physicians will be assisted by a validated and previously published AI-based risk prediction system that estimates the risk for graft loss in the next year, starting from 3 months after randomization until 24 months after randomization. The study population will consist of 122 kidney transplant recipients >12 months after transplantation, who are at least 18 years of age, are able to communicate in German, and have an estimated glomerular filtration rate <30 mL/min/1.73 m2. Patients with multi-organ transplantation, or who are not able to communicate in German, as well as underage patients, cannot participate. For the primary end point, the proportion of patients who have had a conversation about their treatment options after graft loss is compared at 12 months after randomization. Additionally, 2 different assessment tools for SDM, the CollaboRATE mean score and the Control Preference Scale, are compared between the 2 groups at 12 months and 24 months after randomization. Furthermore, recordings of patient-physician conversations, as well as semistructured interviews with patients, support persons, and physicians, are performed to support the quantitative results. Results: The enrollment for the study is ongoing. The first results are expected to be submitted for publication in 2025. Conclusions: This is the first study to examine the influence of AI-based risk prediction on physician-patient interaction in the context of kidney transplantation. We use a mixed methods approach by combining a randomized design with a simple quantitative end point (frequency of conversations), different quantitative measurements for SDM, and several qualitative research methods (eg, records of physician-patient conversations and semistructured interviews) to examine the implementation of AI-based risk prediction in the clinic. Trial Registration: ClinicalTrials.gov NCT06056518; https://clinicaltrials.gov/study/NCT06056518 International Registered Report Identifier (IRRID): PRR1-10.2196/54857

Objective: To improve performance of medical entity normalization across many languages, especially when fewer language resources are available compared to English. Materials and Methods: We propose xMEN, a modular system for cross-lingual (x) medical entity normalization (MEN), accommodating both low- and high-resource scenarios. To account for the scarcity of aliases for many target languages and terminologies, we leverage multilingual aliases via cross-lingual candidate generation. For candidate ranking, we incorporate a trainable cross-encoder (CE) model if annotations for the target task are available. To balance the output of general-purpose candidate generators with subsequent trainable re-rankers, we introduce a novel rank regularization term in the loss function for training CEs. For re-ranking without gold-standard annotations, we introduce multiple new weakly labeled datasets using machine translation and projection of annotations from a high-resource language. Results: xMEN improves the state-of-the-art performance across various benchmark datasets for several European languages. Weakly supervised CEs are effective when no training data is available for the target task. Discussion: We perform an analysis of normalization errors, revealing that complex entities are still challenging to normalize. New modules and benchmark datasets can be easily integrated in the future. Conclusion: xMEN exhibits strong performance for medical entity normalization in many languages, even when no labeled data and few terminology aliases for the target language are available. To enable reproducible benchmarks in the future, we make the system available as an open-source Python toolkit. The pre-trained models and source code are available online: https://github.com/hpi-dhc/xmen