Citations

Abstract Clinical empathy is essential for patient care, but physicians need continually balance emotional warmth with factual precision under the cognitive and emotional constraints of clinical practice. This study investigates how large language models (LLMs) can function as empathy editors, refining physicians’ written responses to enhance empathetic tone while preserving underlying medical information. More importantly, we introduce novel quantitative metrics, an Empathy Ranking Score and a MedFactChecking Score to systematically assess both emotional and factual quality of the responses. Experimental results show that LLM-edited responses significantly increase perceived empathy while preserving factual accuracy compared with fully LLM-generated outputs. These findings suggest that using LLMs as editorial assistants, rather than autonomous generators , offers a safer, more effective pathway to empathetic and trustworthy AI-assisted healthcare communication.

Abstract Introduction Recent literature suggests growing rates of malpractice claims against Urologists, with the incidence of being sued seeming to be unrelated to one’s professional reputation. These cases provide insight into errors that may lead to litigation. Given national trends of rising malpractice cases, estimates that a Urologist can expect to be sued at least twice in their careers are likely underestimates. Malpractice cases can give insight into the common medical errors rising to the level of litigation. Given the elective nature of procedures within sexual medicine, understanding litigation related to these cases is crucial. Objective We aim to analyze malpractice suits related to men’s health and highlight clinical presentations and legal outcomes. Methods Per STROBE guidelines, we searched the publicly available Thomson Reuters Westlaw legal database for “jury verdicts and settlements” from January 1970 to August 2023 to identify medical malpractice cases in Urology. Patient demographics, clinical presentation, alleged error, and legal outcomes were abstracted during full case review by an independent screener. Cases related to men’s sexual health or fertility that named a urologist as the defendant were fully analyzed. Results A total of 553 Urology cases were extracted, with 23 men’s health related cases subsequently analyzed and summarized in Table 1. The most common conditions associated with litigation were erectile dysfunction (penile prosthesis) (39%), epidydimal pathology (13%), and varicocele (13%). The most common allegations were misdiagnosis (26%), surgical complication (22%), lack of informed consent (22%), and violation of standard of care (22%). Of the 23 cases, 57% ruled “no liability” in favor of the urologist, 39% ruled in favor of the plaintiff with a median award of $335,000 (IQR = 100,000-450,000), and one was settled for $316,338. Among cases ruled as negligent, performing the incorrect procedure, surgical complications, and violating the standard of care were prominent allegations. Florida (26%) and Pennsylvania (17%) had the most cases in this sample. Of note, there were no cases for penile plication, plaque excision, microsurgical cord denervation, vasectomy reversal, or sperm retrieval, and only one for vasectomy. Conclusions This study characterizes malpractice cases related to men’s sexual health naming urologists as defendants. Despite fear of litigation, this review of the Westlaw database revealed only 23 cases related to men’s health since 1970. Moreover, the majority of cases ruled in favor of the Urologist. Obtaining comprehensive informed consent, following national guidelines, and responding appropriately to surgical complications may minimize likelihood of litigation and maximize patient outcomes. Disclosure No.

ABSTRACT Background Large language model (LLM) chatbots, a form of artificial intelligence (AI) that excels at prompt‐based interactions and mimics human conversation, have emerged as a tool for providing patients with information about urologic conditions. We aimed to examine the quality of information related to benign prostatic hyperplasia surgery from four chatbots and how they would respond to sample patient messages. Methods We identified the top three queries in Google Trends related to “treatment for enlarged prostate.” These were entered into ChatGPT (OpenAI), Bard (Google), Bing AI (Microsoft), and Doximity GPT (Doximity), both unprompted and prompted for specific criteria (optimized). The chatbot‐provided answers to each query were evaluated for overall quality by three urologists using the DISCERN instrument. Readability was measured with the built‐in Flesch–Kincaid reading level tool in Microsoft Word. To assess the ability of chatbots to answer patient questions, we prompted the chatbots with a clinical scenario related to holmium laser enucleation of the prostate, followed by 10 questions that the National Institutes of Health recommends patients ask before surgery. Accuracy and completeness of responses were graded with Likert scales. Results Without prompting, the quality of information was moderate across all chatbots but improved significantly with prompting (mean [SD], 3.3 [1.2] vs. 4.4 [0.7] out of 5; p < 0.001). When answering simulated patient messages, the chatbots were accurate (mean [SD], 5.6 [0.4] out of 6) and complete (mean [SD], 2.8 [0.3] out of 3). Additionally, 98% (39/40) had a median score of 5 or higher for accuracy, which corresponds to “nearly all correct.” The readability was poor, with a mean (SD) Flesch–Kincaid reading level grade of 12.1 (1.3) (unprompted). Conclusions LLM chatbots hold promise for patient education, but their effectiveness is limited by the need for careful prompting from the user and by responding at a reading level higher than that of most Americans (grade 8). Educating patients and physicians on optimal LLM interaction is crucial to unlock the full potential of chatbots.

Abstract Introduction Despite direct access to clinicians through the electronic health record, patients are increasingly turning to the internet for information related to their health, especially with sensitive urologic conditions such as Peyronie’s disease (PD). Large language model (LLM) chatbots are a form of artificial intelligence that rely on user prompts to mimic conversation, and they have shown remarkable capabilities. The conversational nature of these chatbots has the potential to answer patient questions related to PD; however, the accuracy, comprehensiveness, and readability of these LLMs related to PD remain unknown. Aims To assess the quality and readability of information generated from 4 LLMs with searches related to PD; to see if users could improve responses; and to assess the accuracy, completeness, and readability of responses to artificial preoperative patient questions sent through the electronic health record prior to undergoing PD surgery. Methods The National Institutes of Health’s frequently asked questions related to PD were entered into 4 LLMs, unprompted and prompted. The responses were evaluated for overall quality by the previously validated DISCERN questionnaire. Accuracy and completeness of LLM responses to 11 presurgical patient messages were evaluated with previously accepted Likert scales. All evaluations were performed by 3 independent reviewers in October 2023, and all reviews were repeated in April 2024. Descriptive statistics and analysis were performed. Results Without prompting, the quality of information was moderate across all LLMs but improved to high quality with prompting. LLMs were accurate and complete, with an average score of 5.5 of 6.0 (SD, 0.8) and 2.8 of 3.0 (SD, 0.4), respectively. The average Flesch-Kincaid reading level was grade 12.9 (SD, 2.1). Chatbots were unable to communicate at a grade 8 reading level when prompted, and their citations were appropriate only 42.5% of the time. Conclusion LLMs may become a valuable tool for patient education for PD, but they currently rely on clinical context and appropriate prompting by humans to be useful. Unfortunately, their prerequisite reading level remains higher than that of the average patient, and their citations cannot be trusted. However, given their increasing uptake and accessibility, patients and physicians should be educated on how to interact with these LLMs to elicit the most appropriate responses. In the future, LLMs may reduce burnout by helping physicians respond to patient messages.

Synchronization of local and distributed neuronal assemblies is thought to underlie fundamental brain processes such as perception, learning, and cognition. In neurological disease, neuronal synchrony can be altered and in epilepsy may play an important role in the generation of seizures. Linear cross-correlation and mean phase coherence of local field potentials (LFPs) are commonly used measures of neuronal synchrony and have been studied extensively in epileptic brain. Multiple studies have reported that epileptic brain is characterized by increased neuronal synchrony except possibly prior to seizure onset when synchrony may decrease. Previous studies using intracranial electroencephalography (EEG), however, have been limited to patients with epilepsy. Here we investigate neuronal synchrony in epileptic and control brain using intracranial EEG recordings from patients with medically resistant partial epilepsy and control subjects with intractable facial pain. For both epilepsy and control patients, average LFP synchrony decreases with increasing interelectrode distance. Results in epilepsy patients show lower LFP synchrony between seizure-generating brain and other brain regions. This relative isolation of seizure-generating brain underlies the paradoxical finding that control patients without epilepsy have greater average LFP synchrony than patients with epilepsy. In conclusion, we show that in patients with focal epilepsy, the region of epileptic brain generating seizures is functionally isolated from surrounding brain regions. We further speculate that this functional isolation may contribute to spontaneous seizure generation and may represent a clinically useful electrophysiological signature for mapping epileptic brain.