Large Language Models-Assisted Diagnosis of Catecholaminergic Polymorphic Ventricular Tachycardia in a Pediatric Cardiac Arrest Patient | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Case Report Large Language Models-Assisted Diagnosis of Catecholaminergic Polymorphic Ventricular Tachycardia in a Pediatric Cardiac Arrest Patient Xiangxin Liao, Chao Lei, Xiaxia Zheng, Wen Wu, Xiaoyun Xu, ZhaoHui Zhang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6384159/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background : Catecholaminergic polymorphic ventricular tachycardia (CPVT), a rare hereditary ion channel disorder, is triggered by exercise or stress, causing PVT and sudden death. Diagnosis is tough, especially with cardiac arrest as the initial symptom, and guideline - recommended adrenaline may worsen it. Large language models offers new ways to identify it quickly. Case Presentation : A 7 - year - old boy had sudden cardiac arrest during rope - skipping. After resuscitation, defibrillation, and adrenaline, his circulation returned, but PVT persisted. VA - ECMO in our hospital couldn't control the arrhythmia. Multidisciplinary discussion was inconclusive. ChatGPT and DeepSeek suggested CPVT. After stopping catecholamines and using beta - blockers, arrhythmias decreased. Gene testing confirmed an RYR2 gene mutation (c.6737C>T), diagnosing CPVT. However, due to long - term resuscitation, late diagnosis, and delayed ECMO, the child developed severe complications. Despite successful ECMO weaning, the parents gave up treatment, and the child died. Conclusion: CPVT patients with cardiac arrest are critically ill and hard to diagnose. Early detection and targeted treatment are vital for prognosis. Large language models have value in CPVT diagnosis but should be combined with clinical judgment and further tests. For children with unexplained cardiac arrest, Large language models - assisted consultation can be considered, and clinicians should better understand rare diseases like CPVT for more timely and accurate diagnoses. Clinical trial number No applicable. Catecholaminergic polymorphic ventricular tachycardia Large language models Gene testing Figures Figure 1 Figure 2 Figure 3 Figure 4 Background Catecholaminergic polymorphic ventricular tachycardia (CPVT) is an ion channel disorder in which ventricular arrhythmias are induced by emotional or exercise stress. It is a rare cause of polymorphic ventricular tachycardia and sudden death in children and young people [ 1 ]. According to the cardiopulmonary resuscitation(CPR) guidelines [ 2 ]., the use of adrenaline is a first-line treatment for patients with cardiac arrest. However, in CPVT patients with cardiac arrest, the use of catecholamine drugs such as adrenaline may be counterproductive and even life-threatening, which poses a great challenge to the early diagnosis of CPVT. This article reports a case of a 7-year-old child with cardiac arrest. After receiving veno - arterial extracorporeal membrane oxygenation (ECMO) treatment, the child still had frequent episodes of ventricular tachycardia (VT) and ventricular fibrillation (VF). Due to the unclear initial diagnosis, we used Artificial Intelligence (AI) large language model tools to focus on "catecholaminergic polymorphic ventricular tachycardia" as the cause. After discontinuing catecholamine drugs and using β-blockers, the frequency of malignant arrhythmias in the child decreased significantly. Finally, the diagnosis of CPVT was confirmed by genetic testing. Case Presentation A 7-year-old, 23-kg boy was admitted 3 hours after CPR due to "post-exercise convulsions and loss of consciousness". He had fallen while rope - skipping at school, with limb convulsions and then loss of consciousness. The teacher called 120, and CPR was done during transport. At the local hospital, he was in critical condition. Rescuers performed multiple life - saving measures. Subsequently, his spontaneous circulation was restored, and then the family requested to transfer him to our hospital. During the transfer, the child had 5 ~ 6 more "convulsions" like before, with each episode lasting seconds to over ten seconds. The ECG showed VT or VF, so chest compressions, defibrillation, adrenaline, and infusions of norepinephrine and dopamine were given. Fifteen minutes later, the child was admitted to our hospital's PICU. In the PICU, the child's vital signs were monitored, and medications for sedation, analgesia, and anti - arrhythmia were administered. But VT and VF still occurred. After defibrillation, the rhythm became sinus. Due to the child's refractory arrhythmia and unstable hemodynamics, and with the family's consent, the PICU doctors called for the ECMO team from the General Intensive Care Unit (GICU). Catheterizations were done, and VA - ECMO was started for circulatory support. Then the child was transferred to the GICU. Upon checking the medical history and previous hospital records, it was found that on April 27, 2023, the child lost consciousness, fell, and had limb convulsions, upward eye deviation, limb stiffness, and frothing at the mouth while playing basketball. The symptoms lasted 1–2 minutes and then stopped. The child was taken to the PICU. Tests like ECG, echocardiography, Brain computed tomography (CT), magnetic resonance imaging (MRI), Electroencephalogram, and various blood tests showed no significant problems. Doctors recommended genetic testing due to the unclear cause of convulsions, but the family refused. In 2024, the child had syncope episodes while swimming on August 28 and running downstairs on November 25. These episodes were similar to the first one, lasting about 1–2 minutes, and the child recovered without seeking medical help. After transfer to the GICU, laboratory tests showed abnormal results. Myocardial injury markers like cTnI, myoglobin, and CK - MB were elevated. NT - pro - BNP was within the normal range. Arterial blood gas analysis indicated an abnormal pH, PO₂, PCO₂, and Base Excess (BE), while other blood gas and electrolyte values were mostly normal. Blood sugar and Neuron - Specific Enolase (NES) were high, and there were abnormal results in white blood cell - related indicators, procalcitonin, and D - dimer, while liver and kidney functions were normal. The bedside ECG showed sinus rhythm with multiple conduction blocks, ventricular escape beats, and a prolonged QTc interval. Bedside echocardiography revealed left ventricular enlargement, reduced systolic function, and mild valvular regurgitation. The bedside chest X - ray showed a small amount of pulmonary exudation. After admission, the patient received ventilator-assisted ventilation, mild hypothermia treatment, and VA-ECMO for circulatory support. The invasive mean arterial blood pressure fluctuated between 40 ~ 70 mmHg, and norepinephrine and dopamine were continuously infused via intravenous micro-pumps. Despite normal serum potassium levels in the child, polymorphic ventricular arrhythmias occurred frequently (Fig. 1 A). Due to the unclear cause, a hospital-wide multidisciplinary discussion was held on the second day of admission. Acute myocarditis, hypertrophic cardiomyopathy, and common congenital heart diseases were initially excluded. However, the specific cause of cardiac arrest and refractory ventricular tachycardia remained undetermined. We entered the key information (Fig. 2 A): "A 7-year-old male child suffered sudden cardiac arrest during rope skipping. After cardiopulmonary resuscitation, defibrillation, and administration of adrenaline, spontaneous circulation was restored. A bedside ultrasound showed that the diastolic and systolic functions of the heart were fair. However, the child has frequent polymorphic ventricular tachycardia. Even after using VA-ECMO, there are still frequent episodes of PVT (during this period, dopamine and norepinephrine have been used to maintain blood pressure). The child had a history of syncope after exercise one year ago. During hospitalization, examinations such as cardiac ultrasound, ECG, and cranial MRI did not show any obvious abnormalities. What is the most likely diagnosis for this child currently?" into the inference module of the artificial intelligence large language model ChatGPT (OpenAI, San Francisco, California, USA). The model replied (Fig. 2 B): "Given these clinical findings, the most likely diagnosis for this child is Catecholaminergic Polymorphic Ventricular Tachycardia (CPVT)…". We also entered the same information into another artificial intelligence large-language model, DEEPSEEK (Deepseek, Hangzhou, Zhejiang, CHN) (Fig. 2 C), and obtained the same result as ChatGPT: Based on the clinical scenario provided, the most likely diagnosis for this 7-year-old male child is catecholaminergic polymorphic ventricular tachycardia (CPVT) (Fig. 4 D). By searching "Polymorphic Ventricular Tachycardia AND case report" on PubMed (the National Library of Medicine's Search Service for Biomedical Literature), we found case report 6 highly similar to this one, which further increases the credibility of the consistent conclusions drawn by the two large language models (LLMs). With the consent of the child's parents, we sent the child's blood sample for whole-exome gene testing (Kindstar Globalgene Technology, Inc., Wuhan, China) to confirm the diagnosis. Based on the strong recommendation of the artificial intelligence large-language models, we promptly discontinued norepinephrine and dopamine and switched to esmolol. As a result, the child's ventricular arrhythmias decreased significantly by approximately 75% (Fig. 1 B), and the bedside ECG showed sinus rhythm (Fig. 3 ). On the fifth day of admission, the ECG re-examination showed a significant improvement in left ventricular systolic function, with an EF value ≥ 45%, mean arterial pressure ≥ 65 mmHg, and blood lactate ≤ 2 mmol/L. After gradually reducing the ECMO flow rate, the circulation and internal environment remained stable, so the ECMO was removed. After discontinuing sedation and analgesia, the child remained unconscious but could open his eyes spontaneously, without convulsions. The muscle tone of the upper limbs increased paroxysmally, presenting a decorticate rigidity state. After removing the ECMO, a cranial CT scan was performed, which showed diffuse brain swelling, compressed and narrowed ventricles, and ischemic-hypoxic changes. The NSE level remained above 50 ng/ml. On the 14th day of admission, the first-generation gene test results showed (Fig. 4 ) that the child had a heterozygous mutation in the RYR2 gene (chromosome location: chr1:237798237), with a mutation site of c.6737C > T. According to the classification of the American College of Medical Genetics and Genomics (ACMG), it was a pathogenic mutation. No abnormalities were detected in the tests of the child's parents and sister. By further inquiring into the medical history, no sudden deaths of children or adolescents were found in the child's close relatives. Due to long-term resuscitation, late diagnosis, and delayed ECMO, the child developed a severe complication of decorticate rigidity. Despite successful weaning from ECMO, on the 18th day of hospitalization, the parents gave up treatment, and the child was discharged with a fatal outcome. Discussion and conclusions In this reported case, the child suffered sudden cardiac arrest while skipping rope. Despite cardiopulmonary resuscitation and extracorporeal membrane oxygenation (ECMO) treatment, the child still experienced frequent episodes of VT and VF. Due to the failure to make a timely and accurate diagnosis, the treatment fell into a vicious cycle of "VT/VF - blood pressure drop - circulatory collapse - intravenous injection of adrenaline - recurrence of VT/VF". This suggests that rope - skipping may have induced malignant arrhythmias, and the repeated use of adrenaline led to refractory electrical storms. Hayashi Minoru [ 3 ] and others' research [ 4 ] found that in undiagnosed CPVT patients who received adrenaline treatment during cardiac arrest resuscitation, the risk of ventricular arrhythmia recurrence increased 3.1 - fold (odds ratio [OR] 3.1, 95% confidence interval [CI] 1.4–6.8). Roston Thomas M. and others' research pointed out that in suspected CPVT cases, the use of adrenaline was significantly associated with the occurrence of electrical storms (hazard ratio [HR] 2.89, p = 0.003), and they recommended cautious use of catecholamine drugs such as adrenaline when the cause was unknown. The 2015 European Society of Cardiology Guidelines [ 5 ] (Class IIa recommendation) clearly warned that adrenaline should be avoided in patients with exercise - induced polymorphic VT (evidence level B). However, adrenaline is a first - line drug recommended by cardiopulmonary resuscitation guidelines [ 2 ] 2 , which makes it extremely difficult to identify and diagnose CPVT in children with cardiac arrest at an early stage to avoid the use of adrenaline, especially when there is a lack of clear medical history and family history. It is worth noting that in some CPVT children, the initial symptoms are not cardiac arrest, but cerebral ischemia and hypoxia caused by short - lasting ventricular arrhythmias, leading to syncope, myoclonus, and tonic movements. These symptoms are easily confused with epilepsy, resulting in misdiagnosis [ 6 ]. Literature reports [ 7 ] show that the average time from the first appearance of symptoms to a definite diagnosis in CPVT children is as long as two years, and the misdiagnosis rate at the first diagnosis is 56%. In most cases, this disease is misdiagnosed as vasovagal syncope and epilepsy. In this case, more than a year before the current episode, the child had multiple episodes of exercise - related transient loss of consciousness and syncope. After being urgently taken to the hospital, a series of examinations such as electroencephalogram and cranial CT were performed, but no positive results were found, and it was diagnosed as epilepsy of unknown cause. Unfortunately, at that time, the doctor did not conduct an exercise stress test and relevant electrophysiological examinations on the child, and the child's parents refused the medical advice of genetic testing, ultimately missing the opportunity for early CPVT diagnosis. To identify cardiac arrest caused by CPVT at an early stage, on the one hand, training for emergency, critical care, and pediatric doctors should be enhanced, with a focus on improving their ability to recognize hereditary arrhythmias such as ion channel diseases [ 8 ]. On the other hand, with the rapid development of AI technology [ 9 ], LLMs have also provided new solutions for the early diagnosis of rare diseases. In this case, when multidisciplinary consultations failed to reach a definite conclusion, both ChatGPT and DeepSeek pointed to the diagnosis of CPVT. The consistency of these conclusions greatly strengthened the confidence of clinicians in making decisions. After discontinuing catecholamine drugs and adding β - blockers, the frequency of VT in the child decreased by 75%. Finally, the diagnosis was confirmed through RyR2 gene mutation testing. This practice indicates that general LLMs can achieve a closed - loop application of "decision support - treatment verification - molecular diagnosis" in critical care scenarios [ 10 ]. Regarding the research on the application of AI in clinical scenarios, Young et al. [ 11 ] studied 61 rare pediatric cases and confirmed that the diagnostic accuracy of LLMs is close to that of senior experts. Berg's team's [ 12 ] emergency room study quantified that AI assistance can reduce the diagnosis time by 40% and the hospital stay by 2.3 days. These pieces of evidence suggest that deeply integrating AI into the clinical pathway may be the key strategy to solve the problem of "diagnostic delay". Although more and more medical professional LLMs tools [ 9 ][ 13 ] are emerging, these tools may be closed - source and chargeable. Therefore, it is difficult to popularize them in most hospitals in the short term. However, general LLMs represented by ChatGPT and Deepseek are tools that any clinician can use for free at any time and are easy to operate [ 14 ], which greatly promotes the practicality of LLMs in the medical field. Of course, general LLMs also have some limitations in medical applications [ 15 ]. The medical knowledge of the models is limited by the time point of the training data and cannot be updated in real - time with the latest research results or clinical guidelines. There is a lack of a specific medical knowledge activation mechanism, and the integration ability of professional terms and multimodal data (such as genomics and imaging) is limited, affecting the design effect of personalized treatment plans. The core basis for the diagnosis of CPVT [ 16 ] is syncope and ventricular arrhythmias induced by exercise or emotion, combined with positive results of an exercise stress test. However, genetic testing also has important value in the diagnosis of CPVT. In this case, genetic testing revealed a heterozygous mutation in the RYR2 gene of the child, further confirming the diagnosis of CPVT. The genetic test results of the child's parents and sister were all negative, indicating that this mutation was a de novo mutation, which may explain the absence of a family history of sudden death among the child's close relatives. In conclusion, for CPVT patients with sudden cardiac arrest, due to the rarity of the disease and the urgency of the situation, making a clear diagnosis in a short time poses a great challenge. Early identification and targeted treatment are crucial for improving the prognosis of patients. The application of AI LLMs in the auxiliary diagnosis of rare diseases provides clinicians with new tools. However, their application still needs to be combined with clinicians' judgment and further examination results. Abbreviations CPVT Catecholaminergic Polymorphic Ventricular Tachycardia VA-ECMO Veno-Arterial Extracorporeal Membrane Oxygenation ICU Intensive Care Unit PICU Pediatric Intensive Care Unit ECG Electrocardiogram VT Ventricular Tachycardia VF Ventricular Fibrillation RyR2 Ryanodine Receptor 2 cTnI Cardiac Troponin I CK-MB Creatine Kinase-MB NT-pro-BNP N-terminal pro-B-type Natriuretic Peptide NES Neuron-Specific Enolase ACMG American College of Medical Genetics and Genomics LLMs Large Language Models AI Artificial Intelligence ESC European Society of Cardiology HRS Heart Rhythm Society EHRA European Heart Rhythm Association APHRS Asia Pacific Heart Rhythm Society PO 2 Partial Pressure of Oxygen PCO₂ Partial Pressure of Carbon Dioxide HCO3⁻ Bicarbonate BE Base Excess WBC White Blood Cell Count NEUT Neutrophil Percentage Hb Hemoglobin ECG Electrocardiogram APTT Activated Partial Thromboplastin Time HR Hazard Ratio OR Odds Ratio CI Confidence Interval Declarations Acknowledgements We would like to convey our heartfelt thanks to the dedicated teams in the ICU and PICU. Their unwavering commitment and vast expertise were crucial in handling this complex case. Our sincere appreciation also goes out to the parents of the young patient. Their steadfast support and trust during this difficult time were indispensable. It is because of them that we are able to present this case. We hope that by sharing it, we can contribute to better care for children affected by CPVT. Author contributions XL and CL were involved in patient management and data collection. XZ, WW, XX, GZ, and ZZ participated in patient management, created Figures 1-4, and refined the manuscript. XQ was responsible for the study design and drafted the manuscript. All authors reviewed the manuscript. Funding None. Data availability The author confirms that all data generated or analysed during this study are included in the manuscript. Ethics approval and consent to participate Our hospital’s ethics review board approved this study. Written informed consent from the patient was also obtained for publication of this case report. Ethical Review Approval Number: 2025-007-01. Consent for publication Written informed consent was obtained from the father of the child patient upon the publication of this article. The content of the consent covers personal or clinical details, as well as any identifying images in this case report. Competing interests The authors declare no competing interests. References Henriquez E, Hernandez EA, Mundla SR, et al. Catecholaminergic polymorphic ventricular tachycardia and gene therapy: a comprehensive review of the literature. Cureus. 2023;15:e47974. Perman SM, Elmer J, Maciel CB, et al. 2023 american heart association focused update on adult advanced cardiovascular life support: an update to the american heart association guidelines for cardiopulmonary resuscitation and emergency cardiovascular care. Circulation. 2024;149:e254–73. Hayashi M, Denjoy I, Extramiana F, et al. Incidence and risk factors of arrhythmic events in catecholaminergic polymorphic ventricular tachycardia. Circulation. 2009;119:2426–34. Roston TM, Wei J, Guo W, et al. Clinical and functional characterization of ryanodine receptor 2 variants implicated in calcium-release deficiency syndrome. JAMA Cardiol. 2022;7:84–92. Priori SG, Blomström-Lundqvist C, Mazzanti A et al. 2015 ESC guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death: the task force for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death of the european society of cardiology (ESC)endorsed by: association for european paediatric and congenital cardiology (AEPC). Eur: Eur Pacing Arrhythm Card Electrophysiol: J Work Groups Card Pacing Arrhythm Card Cell Electrophysiol Eur Soc Cardiol. 2015;17:1601–87. Shabanian R, Ahani M, Zandiyeh S, et al. A case of catecholaminergic polymorphic ventricular tachycardia masquerading as an intractable seizure. Ann Pediatr Cardiol. 2020;13:141–3. Roston TM, Vinocur JM, Maginot KR, et al. Catecholaminergic polymorphic ventricular tachycardia in children: analysis of therapeutic strategies and outcomes from an international multicenter registry. Circ Arrhythmia Electrophysiol. 2015;8:633–42. Mortamet G, Maisonneuve E, Wroblewski I, et al. Sudden pediatric cardiac arrest with catecholaminergic polymorphic ventricular tachycardia: when epinephrin should be avoided. Resuscitation. 2023;192:109967. Liu X, Liu H, Yang G et al. A generalist medical language model for disease diagnosis assistance. Nat Med. Published Online First: 8 January 2025. Wojtara M, Rana E, Rahman T, et al. Artificial intelligence in rare disease diagnosis and treatment. Clin Transl Sci. 2023;16:2106–11. Young CC, Enichen E, Rivera C, et al. Diagnostic accuracy of a custom large language model on rare pediatric disease case reports. Am J Med Genet A. 2025;197:e63878. Berg HT, van Bakel B, van de Wouw L, et al. ChatGPT and generating a differential diagnosis early in an emergency department presentation. Ann Emerg Med. 2024;83:83–6. Preiksaitis C, Ashenburg N, Bunney G, et al. The role of large language models in transforming emergency medicine: scoping review. JMIR Med Inf. 2024;12:e53787. Liu J, Wang C, Liu S. Utility of ChatGPT in clinical practice. J Med Internet Res. 2023;25:e48568. Zhou Y, Moon C, Szatkowski J, et al. Evaluating ChatGPT responses in the context of a 53-year-old male with a femoral neck fracture: a qualitative analysis. Eur J Orthop Surg Traumatol: Orthop Traumatol. 2024;34:927–55. Priori SG, Wilde AA, Horie M, et al. Executive summary: HRS/EHRA/APHRS expert consensus statement on the diagnosis and management of patients with inherited primary arrhythmia syndromes. Eur: Eur Pacing Arrhythm Card Electrophysiol: J Work Groups Card Pacing Arrhythm Card Cell Electrophysiol Eur Soc Cardiol. 2013;15:1389–406. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6384159","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Case Report","associatedPublications":[],"authors":[{"id":440135909,"identity":"90d76145-3fa6-4b04-a246-0da46bf5c376","order_by":0,"name":"Xiangxin Liao","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Xiangxin","middleName":"","lastName":"Liao","suffix":""},{"id":440135910,"identity":"c88f649a-36d0-4c72-a11c-dedfcc5c1cd0","order_by":1,"name":"Chao Lei","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Chao","middleName":"","lastName":"Lei","suffix":""},{"id":440135911,"identity":"7a74a4f2-4ee7-4dd1-9a17-582cd8bbe1b0","order_by":2,"name":"Xiaxia Zheng","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Xiaxia","middleName":"","lastName":"Zheng","suffix":""},{"id":440135912,"identity":"3a2caff3-53ff-4f5f-b151-664c96f66811","order_by":3,"name":"Wen Wu","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Wu","suffix":""},{"id":440135913,"identity":"d4c36170-0397-4257-a8ea-383309e91c85","order_by":4,"name":"Xiaoyun Xu","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Xiaoyun","middleName":"","lastName":"Xu","suffix":""},{"id":440135914,"identity":"b223c093-4696-42ec-8027-2a0eeb556f67","order_by":5,"name":"ZhaoHui Zhang","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"ZhaoHui","middleName":"","lastName":"Zhang","suffix":""},{"id":440135915,"identity":"5ebf7c1e-f94a-4998-a31b-dd32dd09bad0","order_by":6,"name":"Gaosheng Zhou","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Gaosheng","middleName":"","lastName":"Zhou","suffix":""},{"id":440135916,"identity":"751f6494-1f3b-4e80-98f4-f64ec3f437cb","order_by":7,"name":"Xingguang Qu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABKUlEQVRIie2RMUvEMBTHUwrtkp5rbjj9Cj26HNyXSRAuS05ukg5nCSi9RexaEb2vcG6OLYF2qeAkGRwUwU0ouIgcYq7UTlFvdMhvePwJ+ZH3XgAwGP4pWRfqEO222d5KsfK0GgXA2UL5xhbeSUj4X0pPsqGYfRyR5GJxJzyOaLJc3CMQjgl3bzOd0pcTLM7PSpI+VLP88gZN0wIeIlBRwuEB1im+3M+Ed1oQLhnOXis0XTlwgqxYEI6gr1cIb5TlRvFiRP1G+fxNUa/A9zlZSZrlSsG+4xbI4j8r/eoFq6mz4FoyoJaMhmnB7BEuaBBDplV6JQve4DoaXEn6XNdhtLdzXD7Jej4eJG6lVZp/VMOq2rWhwmZVjvZ+q4B1pIr72B51wWAwGAwNXyt9clgS29UcAAAAAElFTkSuQmCC","orcid":"","institution":"China Three Gorges University","correspondingAuthor":true,"prefix":"","firstName":"Xingguang","middleName":"","lastName":"Qu","suffix":""}],"badges":[],"createdAt":"2025-04-06 00:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6384159/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6384159/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80329806,"identity":"2c412f39-97db-44aa-a2c2-98e63a3238fe","added_by":"auto","created_at":"2025-04-10 15:05:45","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":825126,"visible":true,"origin":"","legend":"\u003cp\u003e(A) The child still had frequent polymorphic ventricular arrhythmias after ECMO treatment. (B) After considering CPVT as suggested by ChatGPT/DeepSeek, norepinephrine and dopamine were immediately discontinued, and the beta-blocker esmolol was used. As a result, the child's ventricular arrhythmias decreased significantly.\u003c/p\u003e","description":"","filename":"image1.png","url":"https://assets-eu.researchsquare.com/files/rs-6384159/v1/a9b8dbcab1c050481d9b81be.png"},{"id":80328154,"identity":"4258c0b6-31bb-426d-b103-e789471de70c","added_by":"auto","created_at":"2025-04-10 14:49:45","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":281509,"visible":true,"origin":"","legend":"\u003cp\u003e(A) Input an objective description of the onset and treatment process of the child patient into ChatGPT; (B) ChatGPT speculates that the most likely diagnosis is CPVT; (C) Input the same information and question into DeepSeek; (D) DeepSeek speculates that the most likely diagnosis is CPVT.\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-6384159/v1/a94205cf3be1500c059c814f.png"},{"id":80328157,"identity":"83726aef-46c8-490d-a6f6-46f78a4774ac","added_by":"auto","created_at":"2025-04-10 14:49:45","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":652172,"visible":true,"origin":"","legend":"\u003cp\u003eElectrocardiogram on the 4th day after admission, 3 days after discontinuing catecholamine drugs and switching to esmolol treatment: Sinus rhythm at 86 beats per minute.\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-6384159/v1/0aca9421c862f04b17779c2f.png"},{"id":80328159,"identity":"933f82b2-0e5c-4945-938e-c20237a12ee3","added_by":"auto","created_at":"2025-04-10 14:49:45","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":479633,"visible":true,"origin":"","legend":"\u003cp\u003eFirst-generation gene sequencing results. The arrow indicates that a C\u0026gt;T mutation has occurred at a specific position on chromosome 1 (chr1:237798237) and in exon 44 of the Ryanodine receptor 2 (RyR2), resulting in the substitution of serine with leucine at amino acid position 2246 in the protein.\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-6384159/v1/4ea1ac18fa3324bfd33333e3.png"},{"id":81209512,"identity":"82cf7f7f-b54f-46e3-8c1e-ec26690e2f5f","added_by":"auto","created_at":"2025-04-23 13:02:03","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2455685,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6384159/v1/8b27d971-9c47-4faf-b57b-95f31295516b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Large Language Models-Assisted Diagnosis of Catecholaminergic Polymorphic Ventricular Tachycardia in a Pediatric Cardiac Arrest Patient","fulltext":[{"header":"Background","content":"\u003cp\u003eCatecholaminergic polymorphic ventricular tachycardia (CPVT) is an ion channel disorder in which ventricular arrhythmias are induced by emotional or exercise stress. It is a rare cause of polymorphic ventricular tachycardia and sudden death in children and young people [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. According to the cardiopulmonary resuscitation(CPR) guidelines [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]., the use of adrenaline is a first-line treatment for patients with cardiac arrest. However, in CPVT patients with cardiac arrest, the use of catecholamine drugs such as adrenaline may be counterproductive and even life-threatening, which poses a great challenge to the early diagnosis of CPVT. This article reports a case of a 7-year-old child with cardiac arrest. After receiving veno - arterial extracorporeal membrane oxygenation (ECMO) treatment, the child still had frequent episodes of ventricular tachycardia (VT) and ventricular fibrillation (VF). Due to the unclear initial diagnosis, we used Artificial Intelligence (AI) large language model tools to focus on \"catecholaminergic polymorphic ventricular tachycardia\" as the cause. After discontinuing catecholamine drugs and using β-blockers, the frequency of malignant arrhythmias in the child decreased significantly. Finally, the diagnosis of CPVT was confirmed by genetic testing.\u003c/p\u003e"},{"header":"Case Presentation","content":"\u003cp\u003eA 7-year-old, 23-kg boy was admitted 3 hours after CPR due to \"post-exercise convulsions and loss of consciousness\". He had fallen while rope - skipping at school, with limb convulsions and then loss of consciousness. The teacher called 120, and CPR was done during transport. At the local hospital, he was in critical condition. Rescuers performed multiple life - saving measures. Subsequently, his spontaneous circulation was restored, and then the family requested to transfer him to our hospital.\u003c/p\u003e \u003cp\u003eDuring the transfer, the child had 5 ~ 6 more \"convulsions\" like before, with each episode lasting seconds to over ten seconds. The ECG showed VT or VF, so chest compressions, defibrillation, adrenaline, and infusions of norepinephrine and dopamine were given. Fifteen minutes later, the child was admitted to our hospital's PICU. In the PICU, the child's vital signs were monitored, and medications for sedation, analgesia, and anti - arrhythmia were administered. But VT and VF still occurred. After defibrillation, the rhythm became sinus. Due to the child's refractory arrhythmia and unstable hemodynamics, and with the family's consent, the PICU doctors called for the ECMO team from the General Intensive Care Unit (GICU). Catheterizations were done, and VA - ECMO was started for circulatory support. Then the child was transferred to the GICU.\u003c/p\u003e \u003cp\u003eUpon checking the medical history and previous hospital records, it was found that on April 27, 2023, the child lost consciousness, fell, and had limb convulsions, upward eye deviation, limb stiffness, and frothing at the mouth while playing basketball. The symptoms lasted 1–2 minutes and then stopped. The child was taken to the PICU. Tests like ECG, echocardiography, Brain computed tomography (CT), magnetic resonance imaging (MRI), Electroencephalogram, and various blood tests showed no significant problems. Doctors recommended genetic testing due to the unclear cause of convulsions, but the family refused. In 2024, the child had syncope episodes while swimming on August 28 and running downstairs on November 25. These episodes were similar to the first one, lasting about 1–2 minutes, and the child recovered without seeking medical help.\u003c/p\u003e \u003cp\u003eAfter transfer to the GICU, laboratory tests showed abnormal results. Myocardial injury markers like cTnI, myoglobin, and CK - MB were elevated. NT - pro - BNP was within the normal range. Arterial blood gas analysis indicated an abnormal pH, PO₂, PCO₂, and Base Excess (BE), while other blood gas and electrolyte values were mostly normal. Blood sugar and Neuron - Specific Enolase (NES) were high, and there were abnormal results in white blood cell - related indicators, procalcitonin, and D - dimer, while liver and kidney functions were normal. The bedside ECG showed sinus rhythm with multiple conduction blocks, ventricular escape beats, and a prolonged QTc interval. Bedside echocardiography revealed left ventricular enlargement, reduced systolic function, and mild valvular regurgitation. The bedside chest X - ray showed a small amount of pulmonary exudation.\u003c/p\u003e \u003cp\u003eAfter admission, the patient received ventilator-assisted ventilation, mild hypothermia treatment, and VA-ECMO for circulatory support. The invasive mean arterial blood pressure fluctuated between 40 ~ 70 mmHg, and norepinephrine and dopamine were continuously infused via intravenous micro-pumps. Despite normal serum potassium levels in the child, polymorphic ventricular arrhythmias occurred frequently (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003eA). Due to the unclear cause, a hospital-wide multidisciplinary discussion was held on the second day of admission. Acute myocarditis, hypertrophic cardiomyopathy, and common congenital heart diseases were initially excluded. However, the specific cause of cardiac arrest and refractory ventricular tachycardia remained undetermined. We entered the key information (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eA): \"A 7-year-old male child suffered sudden cardiac arrest during rope skipping. After cardiopulmonary resuscitation, defibrillation, and administration of adrenaline, spontaneous circulation was restored. A bedside ultrasound showed that the diastolic and systolic functions of the heart were fair. However, the child has frequent polymorphic ventricular tachycardia. Even after using VA-ECMO, there are still frequent episodes of PVT (during this period, dopamine and norepinephrine have been used to maintain blood pressure). The child had a history of syncope after exercise one year ago. During hospitalization, examinations such as cardiac ultrasound, ECG, and cranial MRI did not show any obvious abnormalities. What is the most likely diagnosis for this child currently?\" into the inference module of the artificial intelligence large language model ChatGPT (OpenAI, San Francisco, California, USA). The model replied (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eB): \"Given these clinical findings, the most likely diagnosis for this child is Catecholaminergic Polymorphic Ventricular Tachycardia (CPVT)…\". We also entered the same information into another artificial intelligence large-language model, DEEPSEEK (Deepseek, Hangzhou, Zhejiang, CHN) (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eC), and obtained the same result as ChatGPT: Based on the clinical scenario provided, the most likely diagnosis for this 7-year-old male child is catecholaminergic polymorphic ventricular tachycardia (CPVT) (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003eD). By searching \"Polymorphic Ventricular Tachycardia AND case report\" on PubMed (the National Library of Medicine's Search Service for Biomedical Literature), we found case report \u003csup\u003e\u003cb\u003e6\u003c/b\u003e\u003c/sup\u003e highly similar to this one, which further increases the credibility of the consistent conclusions drawn by the two large language models (LLMs). With the consent of the child's parents, we sent the child's blood sample for whole-exome gene testing (Kindstar Globalgene Technology, Inc., Wuhan, China) to confirm the diagnosis. Based on the strong recommendation of the artificial intelligence large-language models, we promptly discontinued norepinephrine and dopamine and switched to esmolol. As a result, the child's ventricular arrhythmias decreased significantly by approximately 75% (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003eB), and the bedside ECG showed sinus rhythm (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). On the fifth day of admission, the ECG re-examination showed a significant improvement in left ventricular systolic function, with an EF value ≥ 45%, mean arterial pressure ≥ 65 mmHg, and blood lactate ≤ 2 mmol/L. After gradually reducing the ECMO flow rate, the circulation and internal environment remained stable, so the ECMO was removed. After discontinuing sedation and analgesia, the child remained unconscious but could open his eyes spontaneously, without convulsions. The muscle tone of the upper limbs increased paroxysmally, presenting a decorticate rigidity state. After removing the ECMO, a cranial CT scan was performed, which showed diffuse brain swelling, compressed and narrowed ventricles, and ischemic-hypoxic changes. The NSE level remained above 50 ng/ml. On the 14th day of admission, the first-generation gene test results showed (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e) that the child had a heterozygous mutation in the RYR2 gene (chromosome location: chr1:237798237), with a mutation site of c.6737C \u0026gt; T. According to the classification of the American College of Medical Genetics and Genomics (ACMG), it was a pathogenic mutation. No abnormalities were detected in the tests of the child's parents and sister. By further inquiring into the medical history, no sudden deaths of children or adolescents were found in the child's close relatives.\u003c/p\u003e \u003cp\u003eDue to long-term resuscitation, late diagnosis, and delayed ECMO, the child developed a severe complication of decorticate rigidity. Despite successful weaning from ECMO, on the 18th day of hospitalization, the parents gave up treatment, and the child was discharged with a fatal outcome.\u003c/p\u003e "},{"header":"Discussion and conclusions","content":"\u003cp\u003eIn this reported case, the child suffered sudden cardiac arrest while skipping rope. Despite cardiopulmonary resuscitation and extracorporeal membrane oxygenation (ECMO) treatment, the child still experienced frequent episodes of VT and VF. Due to the failure to make a timely and accurate diagnosis, the treatment fell into a vicious cycle of \"VT/VF - blood pressure drop - circulatory collapse - intravenous injection of adrenaline - recurrence of VT/VF\". This suggests that rope - skipping may have induced malignant arrhythmias, and the repeated use of adrenaline led to refractory electrical storms. Hayashi Minoru [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e] and others' research [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e] found that in undiagnosed CPVT patients who received adrenaline treatment during cardiac arrest resuscitation, the risk of ventricular arrhythmia recurrence increased 3.1 - fold (odds ratio [OR] 3.1, 95% confidence interval [CI] 1.4–6.8). Roston Thomas M. and others' research pointed out that in suspected CPVT cases, the use of adrenaline was significantly associated with the occurrence of electrical storms (hazard ratio [HR] 2.89, p = 0.003), and they recommended cautious use of catecholamine drugs such as adrenaline when the cause was unknown. The 2015 European Society of Cardiology Guidelines [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e] (Class IIa recommendation) clearly warned that adrenaline should be avoided in patients with exercise - induced polymorphic VT (evidence level B). However, adrenaline is a first - line drug recommended by cardiopulmonary resuscitation guidelines [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]\u003csup\u003e\u003cb\u003e2\u003c/b\u003e\u003c/sup\u003e, which makes it extremely difficult to identify and diagnose CPVT in children with cardiac arrest at an early stage to avoid the use of adrenaline, especially when there is a lack of clear medical history and family history.\u003c/p\u003e\u003cp\u003eIt is worth noting that in some CPVT children, the initial symptoms are not cardiac arrest, but cerebral ischemia and hypoxia caused by short - lasting ventricular arrhythmias, leading to syncope, myoclonus, and tonic movements. These symptoms are easily confused with epilepsy, resulting in misdiagnosis [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Literature reports [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e] show that the average time from the first appearance of symptoms to a definite diagnosis in CPVT children is as long as two years, and the misdiagnosis rate at the first diagnosis is 56%. In most cases, this disease is misdiagnosed as vasovagal syncope and epilepsy. In this case, more than a year before the current episode, the child had multiple episodes of exercise - related transient loss of consciousness and syncope. After being urgently taken to the hospital, a series of examinations such as electroencephalogram and cranial CT were performed, but no positive results were found, and it was diagnosed as epilepsy of unknown cause. Unfortunately, at that time, the doctor did not conduct an exercise stress test and relevant electrophysiological examinations on the child, and the child's parents refused the medical advice of genetic testing, ultimately missing the opportunity for early CPVT diagnosis.\u003c/p\u003e\u003cp\u003eTo identify cardiac arrest caused by CPVT at an early stage, on the one hand, training for emergency, critical care, and pediatric doctors should be enhanced, with a focus on improving their ability to recognize hereditary arrhythmias such as ion channel diseases [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. On the other hand, with the rapid development of AI technology [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e], LLMs have also provided new solutions for the early diagnosis of rare diseases. In this case, when multidisciplinary consultations failed to reach a definite conclusion, both ChatGPT and DeepSeek pointed to the diagnosis of CPVT. The consistency of these conclusions greatly strengthened the confidence of clinicians in making decisions. After discontinuing catecholamine drugs and adding β - blockers, the frequency of VT in the child decreased by 75%. Finally, the diagnosis was confirmed through RyR2 gene mutation testing. This practice indicates that general LLMs can achieve a closed - loop application of \"decision support - treatment verification - molecular diagnosis\" in critical care scenarios [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Regarding the research on the application of AI in clinical scenarios, Young et al. [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] studied 61 rare pediatric cases and confirmed that the diagnostic accuracy of LLMs is close to that of senior experts. Berg's team's [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] emergency room study quantified that AI assistance can reduce the diagnosis time by 40% and the hospital stay by 2.3 days. These pieces of evidence suggest that deeply integrating AI into the clinical pathway may be the key strategy to solve the problem of \"diagnostic delay\".\u003c/p\u003e\u003cp\u003eAlthough more and more medical professional LLMs tools [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e][\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] are emerging, these tools may be closed - source and chargeable. Therefore, it is difficult to popularize them in most hospitals in the short term. However, general LLMs represented by ChatGPT and Deepseek are tools that any clinician can use for free at any time and are easy to operate [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e], which greatly promotes the practicality of LLMs in the medical field. Of course, general LLMs also have some limitations in medical applications [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. The medical knowledge of the models is limited by the time point of the training data and cannot be updated in real - time with the latest research results or clinical guidelines. There is a lack of a specific medical knowledge activation mechanism, and the integration ability of professional terms and multimodal data (such as genomics and imaging) is limited, affecting the design effect of personalized treatment plans.\u003c/p\u003e\u003cp\u003eThe core basis for the diagnosis of CPVT [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] is syncope and ventricular arrhythmias induced by exercise or emotion, combined with positive results of an exercise stress test. However, genetic testing also has important value in the diagnosis of CPVT. In this case, genetic testing revealed a heterozygous mutation in the RYR2 gene of the child, further confirming the diagnosis of CPVT. The genetic test results of the child's parents and sister were all negative, indicating that this mutation was a de novo mutation, which may explain the absence of a family history of sudden death among the child's close relatives.\u003c/p\u003e\u003cp\u003eIn conclusion, for CPVT patients with sudden cardiac arrest, due to the rarity of the disease and the urgency of the situation, making a clear diagnosis in a short time poses a great challenge. Early identification and targeted treatment are crucial for improving the prognosis of patients. The application of AI LLMs in the auxiliary diagnosis of rare diseases provides clinicians with new tools. However, their application still needs to be combined with clinicians' judgment and further examination results.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eCPVT\u0026nbsp;\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Catecholaminergic Polymorphic Ventricular Tachycardia\u003c/p\u003e\n\u003cp\u003eVA-ECMO\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Veno-Arterial Extracorporeal Membrane Oxygenation\u003c/p\u003e\n\u003cp\u003eICU\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Intensive Care Unit\u003c/p\u003e\n\u003cp\u003ePICU\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Pediatric Intensive Care Unit\u003c/p\u003e\n\u003cp\u003eECG \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Electrocardiogram\u003c/p\u003e\n\u003cp\u003eVT \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Ventricular Tachycardia\u003c/p\u003e\n\u003cp\u003eVF\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Ventricular Fibrillation\u003c/p\u003e\n\u003cp\u003eRyR2 \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;\u0026nbsp;Ryanodine Receptor 2\u003c/p\u003e\n\u003cp\u003ecTnI \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Cardiac Troponin I\u003c/p\u003e\n\u003cp\u003eCK-MB\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; Creatine Kinase-MB\u003c/p\u003e\n\u003cp\u003eNT-pro-BNP\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;\u003c/strong\u003eN-terminal pro-B-type Natriuretic Peptide\u003c/p\u003e\n\u003cp\u003eNES \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003eNeuron-Specific Enolase\u003c/p\u003e\n\u003cp\u003eACMG\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003eAmerican\u0026nbsp; \u0026nbsp; College of Medical Genetics and Genomics\u003c/p\u003e\n\u003cp\u003eLLMs\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; Large Language Models\u003c/p\u003e\n\u003cp\u003eAI\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003c/strong\u003eArtificial Intelligence\u003c/p\u003e\n\u003cp\u003eESC\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003c/strong\u003eEuropean Society of Cardiology\u003c/p\u003e\n\u003cp\u003eHRS\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;\u003c/strong\u003eHeart Rhythm Society\u003c/p\u003e\n\u003cp\u003eEHRA\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;\u003c/strong\u003eEuropean Heart Rhythm Association\u003c/p\u003e\n\u003cp\u003eAPHRS\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003c/strong\u003eAsia Pacific Heart Rhythm Society\u003c/p\u003e\n\u003cp\u003ePO\u003csub\u003e2\u003c/sub\u003e\u003cstrong\u003e\u003csub\u003e\u0026nbsp;\u003c/sub\u003e\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003c/strong\u003ePartial Pressure of Oxygen\u003c/p\u003e\n\u003cp\u003ePCO₂\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; Partial Pressure of Carbon Dioxide\u003c/p\u003e\n\u003cp\u003eHCO3⁻\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp; \u0026nbsp; Bicarbonate\u003c/p\u003e\n\u003cp\u003eBE \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Base Excess\u003c/p\u003e\n\u003cp\u003eWBC \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;White Blood Cell Count\u003c/p\u003e\n\u003cp\u003eNEUT \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Neutrophil Percentage\u003c/p\u003e\n\u003cp\u003eHb \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Hemoglobin\u003c/p\u003e\n\u003cp\u003eECG \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Electrocardiogram\u003c/p\u003e\n\u003cp\u003eAPTT \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Activated Partial Thromboplastin Time\u003c/p\u003e\n\u003cp\u003eHR \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Hazard Ratio\u003c/p\u003e\n\u003cp\u003eOR \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u0026nbsp;Odds Ratio\u003c/p\u003e\n\u003cp\u003eCI \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;Confidence Interval\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe would like to convey our heartfelt thanks to the dedicated teams in the ICU and PICU. Their unwavering commitment and vast expertise were crucial in handling this complex case.\u003c/p\u003e\n\u003cp\u003eOur sincere appreciation also goes out to the parents of the young patient. Their steadfast support and trust during this difficult time were indispensable. It is because of them that we are able to present this case. We hope that by sharing it, we can contribute to better care for children affected by CPVT.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eXL and CL were involved in patient management and data collection. XZ, WW, XX, GZ, and ZZ participated in patient management, created Figures 1-4, and refined the manuscript. XQ was responsible for the study design and drafted the manuscript. All authors reviewed the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNone.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe author confirms that all data generated or analysed during this study are included in the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eOur hospital\u0026rsquo;s ethics review board approved this study. Written informed\u0026nbsp;\u003c/p\u003e\n\u003cp\u003econsent from the patient was also obtained for publication of this case report.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eEthical Review Approval Number: 2025-007-01.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWritten informed consent was obtained from the father of the child patient upon the publication of this article. The content of the consent covers personal or clinical details, as well as any identifying images in this case report.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eHenriquez E, Hernandez EA, Mundla SR, et al. Catecholaminergic polymorphic ventricular tachycardia and gene therapy: a comprehensive review of the literature. Cureus. 2023;15:e47974.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePerman SM, Elmer J, Maciel CB, et al. 2023 american heart association focused update on adult advanced cardiovascular life support: an update to the american heart association guidelines for cardiopulmonary resuscitation and emergency cardiovascular care. Circulation. 2024;149:e254\u0026ndash;73.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHayashi M, Denjoy I, Extramiana F, et al. Incidence and risk factors of arrhythmic events in catecholaminergic polymorphic ventricular tachycardia. Circulation. 2009;119:2426\u0026ndash;34.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoston TM, Wei J, Guo W, et al. Clinical and functional characterization of ryanodine receptor 2 variants implicated in calcium-release deficiency syndrome. JAMA Cardiol. 2022;7:84\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePriori SG, Blomstr\u0026ouml;m-Lundqvist C, Mazzanti A et al. 2015 ESC guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death: the task force for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death of the european society of cardiology (ESC)endorsed by: association for european paediatric and congenital cardiology (AEPC). Eur: Eur Pacing Arrhythm Card Electrophysiol: J Work Groups Card Pacing Arrhythm Card Cell Electrophysiol Eur Soc Cardiol. 2015;17:1601\u0026ndash;87.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eShabanian R, Ahani M, Zandiyeh S, et al. A case of catecholaminergic polymorphic ventricular tachycardia masquerading as an intractable seizure. Ann Pediatr Cardiol. 2020;13:141\u0026ndash;3.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoston TM, Vinocur JM, Maginot KR, et al. Catecholaminergic polymorphic ventricular tachycardia in children: analysis of therapeutic strategies and outcomes from an international multicenter registry. Circ Arrhythmia Electrophysiol. 2015;8:633\u0026ndash;42.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMortamet G, Maisonneuve E, Wroblewski I, et al. Sudden pediatric cardiac arrest with catecholaminergic polymorphic ventricular tachycardia: when epinephrin should be avoided. Resuscitation. 2023;192:109967.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu X, Liu H, Yang G et al. A generalist medical language model for disease diagnosis assistance. Nat Med. Published Online First: 8 January 2025.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWojtara M, Rana E, Rahman T, et al. Artificial intelligence in rare disease diagnosis and treatment. Clin Transl Sci. 2023;16:2106\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYoung CC, Enichen E, Rivera C, et al. Diagnostic accuracy of a custom large language model on rare pediatric disease case reports. Am J Med Genet A. 2025;197:e63878.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBerg HT, van Bakel B, van de Wouw L, et al. ChatGPT and generating a differential diagnosis early in an emergency department presentation. Ann Emerg Med. 2024;83:83\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePreiksaitis C, Ashenburg N, Bunney G, et al. The role of large language models in transforming emergency medicine: scoping review. JMIR Med Inf. 2024;12:e53787.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu J, Wang C, Liu S. Utility of ChatGPT in clinical practice. J Med Internet Res. 2023;25:e48568.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhou Y, Moon C, Szatkowski J, et al. Evaluating ChatGPT responses in the context of a 53-year-old male with a femoral neck fracture: a qualitative analysis. Eur J Orthop Surg Traumatol: Orthop Traumatol. 2024;34:927\u0026ndash;55.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePriori SG, Wilde AA, Horie M, et al. Executive summary: HRS/EHRA/APHRS expert consensus statement on the diagnosis and management of patients with inherited primary arrhythmia syndromes. Eur: Eur Pacing Arrhythm Card Electrophysiol: J Work Groups Card Pacing Arrhythm Card Cell Electrophysiol Eur Soc Cardiol. 2013;15:1389\u0026ndash;406.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"
[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Catecholaminergic polymorphic ventricular tachycardia, Large language models, Gene testing","lastPublishedDoi":"10.21203/rs.3.rs-6384159/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6384159/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground\u003c/strong\u003e: Catecholaminergic polymorphic ventricular tachycardia (CPVT), a rare hereditary ion channel disorder, is triggered by exercise or stress, causing PVT and sudden death. Diagnosis is tough, especially with cardiac arrest as the initial symptom, and guideline - recommended adrenaline may worsen it. Large language models offers new ways to identify it quickly.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCase Presentation\u003c/strong\u003e: A 7 - year - old boy had sudden cardiac arrest during rope - skipping. After resuscitation, defibrillation, and adrenaline, his circulation returned, but PVT persisted. VA - ECMO in our hospital couldn't control the arrhythmia. Multidisciplinary discussion was inconclusive. ChatGPT and DeepSeek suggested CPVT. After stopping catecholamines and using beta - blockers, arrhythmias decreased. Gene testing confirmed an RYR2 gene mutation (c.6737C\u0026gt;T), diagnosing CPVT. However, due to long - term resuscitation, late diagnosis, and delayed ECMO, the child developed severe complications. Despite successful ECMO weaning, the parents gave up treatment, and the child died.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003e CPVT patients with cardiac arrest are critically ill and hard to diagnose. Early detection and targeted treatment are vital for prognosis. Large language models have value in CPVT diagnosis but should be combined with clinical judgment and further tests. For children with unexplained cardiac arrest, Large language models - assisted consultation can be considered, and clinicians should better understand rare diseases like CPVT for more timely and accurate diagnoses.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClinical trial number \u003c/strong\u003e\u0026nbsp;No applicable.\u003c/p\u003e","manuscriptTitle":"Large Language Models-Assisted Diagnosis of Catecholaminergic Polymorphic Ventricular Tachycardia in a Pediatric Cardiac Arrest Patient","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-10 14:49:40","doi":"10.21203/rs.3.rs-6384159/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"
[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8151d815-7a08-4724-83b4-aa6a74807694","owner":[],"postedDate":"April 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-24T13:53:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-10 14:49:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6384159","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6384159","identity":"rs-6384159","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.