Santiago Romero-Brufau MD, PhD , Radit Smunyahirun PhD , Timothée Filhol MiM , Lucille Niederhauser MS , Thanawin Trakoolwilaiwan MS , Gurpreet Singh PhD
{"title":"Vital Signs–Only Machine Learning Model for Acute Inpatient Deterioration: A Retrospective Multicenter Study","authors":"Santiago Romero-Brufau MD, PhD , Radit Smunyahirun PhD , Timothée Filhol MiM , Lucille Niederhauser MS , Thanawin Trakoolwilaiwan MS , Gurpreet Singh PhD","doi":"10.1016/j.mayocpiqo.2025.100663","DOIUrl":"10.1016/j.mayocpiqo.2025.100663","url":null,"abstract":"<div><h3>Objective</h3><div>To develop predictive models that are compatible with vital signs monitoring devices to identify patients at risk of clinical deterioration, defined as requiring a rapid response team intervention or an unplanned intensive care unit transfer.</div></div><div><h3>Patients and Methods</h3><div>Targeted vital signs from 227,858 inpatients admitted to general care or telemetry beds at a multihospital health care institution between January 1, 2019, and July 31, 2023, were selected. After filtering for high-quality data, 30,118 patients were used to train a Light Gradient Boosting Machine, and 30,095 were reserved for blind validation. We developed a machine learning model designed to minimize false positives while maintaining clinical relevance in identifying low-prevalence clinical deterioration events.</div></div><div><h3>Results</h3><div>At a sensitivity of 73.4% (95% CI, 72.2%-74.4%), the model achieved a positive predictive value (PPV) of 30.4% (95% CI, 29.6%-31.3%), with a C-statistic of 0.874 (95% CI, 0.867-0.881), alert rate of 0.170 (95% CI, 0.167-0.173) per patient per day, and normalized alert rate of 2.41 (95% CI, 2.31-2.51). Stratified analysis by hospital revealed that PPV was highest at the Rochester site, reaching 54.9% (95% CI, 52.9%-57.0%) and outperforming the EPIC deterioration index by 46% or a factor of 6 (7.57%).</div></div><div><h3>Conclusion</h3><div>Achieving a high PPV is crucial because it ensures a larger proportion of alerts are true positives, reducing the burden of false alarms. The considerable improvement in results comes from the novel 2-window feature extraction method. This technique enables the model to capture both long-term trends and recent changes in patient status, enhancing predictive performance.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100663"},"PeriodicalIF":0.0,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104709","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chibueze Ogbonnaya MS, PhD , Madison Kindred MS, PhD , Carl J. Lavie MD, FACC , Hannah Oh MPH, ScD , Min-Jeong Shin PhD , Xuemei Sui MD, MPH, PhD , Jason Jaggers MS, PhD , Ryan Porter MS, PhD , Dahyun Park MS, PhD , Jin E. Kim BS , Jessica Gong MS, PhD , Vivek K. Prasad MBBS, MPH, PhD
{"title":"Association Between Trunk Fat Mass Index and Diabetes in a Multinational Population","authors":"Chibueze Ogbonnaya MS, PhD , Madison Kindred MS, PhD , Carl J. Lavie MD, FACC , Hannah Oh MPH, ScD , Min-Jeong Shin PhD , Xuemei Sui MD, MPH, PhD , Jason Jaggers MS, PhD , Ryan Porter MS, PhD , Dahyun Park MS, PhD , Jin E. Kim BS , Jessica Gong MS, PhD , Vivek K. Prasad MBBS, MPH, PhD","doi":"10.1016/j.mayocpiqo.2025.100658","DOIUrl":"10.1016/j.mayocpiqo.2025.100658","url":null,"abstract":"<div><h3>Objective</h3><div>To examine the cross-sectional association between trunk fat mass index (TFMI) and diabetes across individuals within the same body mass index (BMI [calculated as the weight in kilograms divided by the height in meters squared]) categories in a multinational population.</div></div><div><h3>Participants and Methods</h3><div>We harmonized and pooled data on 57,764 individuals aged 40 years and older from the United Kingdom, the United States, and South Korea. Trunk fat mass imaging was performed using a dual-energy X-ray absorptiometry device during 2015-2023 in the United Kingdom, 2011-2018 in the United States, and 2008-2011 in South Korea. The prevalence of diabetes was derived from the self-reported medical history. Additionally, plasma biochemistry analyses were conducted to update the number of participants with diabetes.</div></div><div><h3>Results</h3><div>Among participants classified as having a normal weight based on BMI, the relative risks (RRs) of diabetes increased from TFMI quintiles 1 to 5 with the linear trend (<em>P</em><.001). The risk of diabetes among individuals in TFMI quintile 5 was around 3 times greater than those in quintile 1 (men—RR, 3.06; 95% confidence interval [CI], 2.17-4.34; women—3.35; 95% CI, 2.08-5.39). This significant linear trend (P<.001) in RRs was also present in overweight and obese individuals (overweight men—RR, 1.92; 95% CI, 1.50-2.47; overweight women—RR, 2.25; 95% CI, 1.73-2.91; obese men—RR, 2.47; 95% CI, 1.83-3.35; obese women—2.79; 95% CI, 2.04-3.83).</div></div><div><h3>Conclusion</h3><div>Within a specific BMI category, individuals with a high trunk fat mass are more likely to experience diabetes compared with those with lower levels of central fat.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100658"},"PeriodicalIF":0.0,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145104708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Oliver Moore MBBS , Fran Neveu-Coble BN , Scott Read PhD , Wai-See Ma MBChB , Adnan Nagriel PhD , Anna Di Bartolomeo MBBS , Jacob George PhD , Golo Ahlenstiel PhD
{"title":"Dynamic Changes in Bilirubin Predict 90-Day Mortality in Patients With Hepatocellular Carcinoma and Acute Decompensations of Cirrhosis: The HCC-AD Score","authors":"Oliver Moore MBBS , Fran Neveu-Coble BN , Scott Read PhD , Wai-See Ma MBChB , Adnan Nagriel PhD , Anna Di Bartolomeo MBBS , Jacob George PhD , Golo Ahlenstiel PhD","doi":"10.1016/j.mayocpiqo.2025.100661","DOIUrl":"10.1016/j.mayocpiqo.2025.100661","url":null,"abstract":"<div><h3>Objective</h3><div>To develop a score to predict 90-day mortality in patients with hepatocellular carcinoma (HCC) admitted with an acute decompensation (AD) event of chronic liver disease.</div></div><div><h3>Patients and Methods</h3><div>This retrospective cohort study was conducted at Blacktown and Westmead Hospitals in Australia, including patients with decompensated cirrhosis and concomitant HCC between January 1, 2012, and May 31, 2023. Participants were separated into derivation (n=233) and validation (n=132) cohorts. Demographic and clinical data were collected at admission and day 7. Independent predictors for 90-day transplant-free survival were entered into classification and regression tree analysis to develop the HCC-AD score. Discrimination was assessed in the validation cohort using Harrell C statistic. Subgroup analysis was conducted for each Barcelona Clinic Liver Cancer (BCLC) class with comparisons made to current scores.</div></div><div><h3>Results</h3><div>A cohort of 355 patients was considered. Admission bilirubin (<em>P</em>=.009) and 7-day change in bilirubin (<em>P</em>=.018) remained significant for 90-day mortality in multivariable analysis. The HCC-acute decompensation (AD) score stratified patients into 3 risk groups with predicted mortality of 26%, 49%, and 89%, respectively. The HCC-AD score showed good discrimination (Harrell C=0.731). Cox regression analysis determined the HCC-AD score remained predictive in BCLC B (<em>P</em><.001), C (<em>P</em><.001), and D (<em>P</em>=.010) scored HCC. The model for end-stage liver disease 3.0 (<em>P</em>=.058) and Child-Pugh (<em>P</em>=.11) scores were not predictive in BCLC D HCC.</div></div><div><h3>Conclusion</h3><div>A simple score that stratifies patients with HCC into 3 risk categories based on changes in bilirubin predicts 90-day mortality following an acute decompensatory event. It is superior to other scores in advanced HCC.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100661"},"PeriodicalIF":0.0,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145048362","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Risk of Juvenile Idiopathic Arthritis Following HPV9 Vaccination: A Retrospective Cohort Study Before and During the COVID-19 Pandemic","authors":"Ming-Chin Tsai MD , Hsin-Hua Chen MD, PhD , Wen-Yu Wu MD , Yung-Chieh Huang MD , Chiann-Yi Hsu MSc , Lin-Shien Fu MD","doi":"10.1016/j.mayocpiqo.2025.100647","DOIUrl":"10.1016/j.mayocpiqo.2025.100647","url":null,"abstract":"<div><h3>Objective</h3><div>To evaluate whether 9-valent human papillomavirus (HPV9) vaccination is associated with an increased risk of juvenile idiopathic arthritis (JIA), particularly during the coronavirus disease-2019 (COVID-19) pandemic.</div></div><div><h3>Patients and Methods</h3><div>We conducted a retrospective cohort study using TriNetX U.S. Collaborative Network data from January 1, 2016, to December 31, 2023. Girls aged 9-13 years who received their first HPV9 dose in either the prepandemic (2016-2019) or pandemic (2020-2023) period were matched with unvaccinated controls. Exclusion criteria included previous JIA diagnosis, antirheumatic drug use, or positive rheumatoid factor. Incidence of new-onset JIA was tracked over 8 days to 36 months. Cox regression and Kaplan-Meier survival analysis were used to evaluate hazard ratios (HRs) and JIA-free survival.</div></div><div><h3>Results</h3><div>Among 99,243 vaccinated and 1.1 million control individuals, HPV9 recipients had a significantly reduced risk of JIA at 36 months in both periods (HR 2016-2019, 0.207, <em>P</em><.001; HR 2020-2023, 0.287, <em>P</em><.001). No increased risk was observed during the early postvaccination period. The estimated cumulative probability of JIA did not differ significantly between vaccinated groups across the 2 periods (<em>P</em>=.9), nor among unvaccinated controls (<em>P</em>=.238), indicating no modifying effect from COVID-19.</div></div><div><h3>Conclusion</h3><div>The HPV9 vaccination was associated with a lower risk of JIA, and this effect can last at least for 3 years. The COVID-19 pandemic did not alter this relationship. These findings reinforce the immunological safety of HPV9 and provide reassurance for adolescent vaccination programs, even in pandemic contexts.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100647"},"PeriodicalIF":0.0,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yin Wang MD, PhD , Mengjun Shen MD , Ke Bi MD , Wei Yang MD, PhD , Xiaofei Ye MD, PhD , Qing Tang MD, PhD , Yi Zhang MD , Yang Cong MD , Huiming Zhu MD , Hongwei Chen MD , Chunhong Tang MD , Martin R. Prince MD, PhD
{"title":"A Dual-Modality Ultrasound Video Recognition Model for Distinguishing Subpleural Pulmonary Nodules","authors":"Yin Wang MD, PhD , Mengjun Shen MD , Ke Bi MD , Wei Yang MD, PhD , Xiaofei Ye MD, PhD , Qing Tang MD, PhD , Yi Zhang MD , Yang Cong MD , Huiming Zhu MD , Hongwei Chen MD , Chunhong Tang MD , Martin R. Prince MD, PhD","doi":"10.1016/j.mayocpiqo.2025.100659","DOIUrl":"10.1016/j.mayocpiqo.2025.100659","url":null,"abstract":"<div><h3>Objective</h3><div>To develop a deep learning model based on dual-modality ultrasound (DMUS) video recognition for the differential diagnosis of benign and malignant subpleural pulmonary nodules (SPNs).</div></div><div><h3>Patients and Methods</h3><div>Participant data (n=193, median age, 58 years [IQR, 34-66 years]; 123 men) with SPNs, prospectively collected from January 7, to December 21, 2020, were divided into training (n=154) and validation (n=39) sets in an 8:2 ratio. Additionally, independent internal (n=88) and external (n=91) test sets were prospectively collected from January 10 to June 25, 2021. The nature of the SPNs was determined through biopsy (n=306) and clinical follow-up (n=66). Our model integrated DMUS videos, time-intensity curves, and clinical information. The model’s performance was evaluated using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity and compared with state-of-the-art video classification models, as well as ultrasound and computed tomography diagnoses made by radiologists.</div></div><div><h3>Results</h3><div>In the internal test set, our model accurately distinguished malignant from benign SPNs with an AUC, accuracy, sensitivity, and specificity of 0.91, 91% (80 of 88), 90% (27 of 30), and 91% (53 of 58), outperforming state-of-the-art video classification models (all <em>P</em><.05). In the external test set, the model achieved the accuracy, sensitivity, and specificity of 89% (81 of 91), 84% (27 of 32), and 92% (54 of 59), which were higher than the parameters for radiologist interpretations of ultrasound (81% [74 of 91], 63% [20 of 32], and 92% [54 of 59]) and computed tomography (76% [69 of 91], 91% [29 of 32], and 68% [40 of 59]), respectively.</div></div><div><h3>Conclusion</h3><div>This deep learning model based on DMUS video recognition enhances the performance of ultrasound in differentiating benign from malignant SPNs.</div></div><div><h3>Trial Registration</h3><div><span><span>clinicaltrials.gov</span><svg><path></path></svg></span> Identifier: ChiCTR1800019828</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100659"},"PeriodicalIF":0.0,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145019007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Urbee Disha Peterson DO, MS , Madison Beenken MS , Teng Moua MD
{"title":"Association of Mood or Affect With Respiratory-Related Quality of Life, Lung Function, and All-Cause Mortality in Fibrotic Interstitial Lung Disease","authors":"Urbee Disha Peterson DO, MS , Madison Beenken MS , Teng Moua MD","doi":"10.1016/j.mayocpiqo.2025.100660","DOIUrl":"10.1016/j.mayocpiqo.2025.100660","url":null,"abstract":"<div><h3>Objective</h3><div>To assess whether self-reported acute mood or affect is associated with other patient-reported outcome measures, lung function, and all-cause mortality, in patients with fibrotic interstitial lung disease (f-ILD).</div></div><div><h3>Patients and Methods</h3><div>The Positive and Negative Affect Schedule (PANAS) is a 20-item questionnaire reflecting recent mood or affect over the past week, reported as Positive, Negative, or Ratio (Positive:Negative) subscores. Baseline and serial PANAS scores were assessed for their correlation with the Chronic Respiratory Questionnaire, Self-Management Assessment Scale 30, and lung function over a 3-year study period, and association with incident anxiety, depression, and all-cause mortality.</div></div><div><h3>Results</h3><div>In total, 199 patients with f-ILD were enrolled. Baseline PANAS scores correlated moderately with Chronic Respiratory Questionnaire and Self-Management Assessment Scale 30 scores. Higher PANAS Positive and Ratio scores were associated with higher percent predicted forced vital capacity. Mean PANAS scores were higher or lower when stratified by clinically suspected anxiety and/or depression and predictive of all-cause mortality on adjusted analysis, respectively. Incident anxiety and/or depression was not associated with worse survival outcome.</div></div><div><h3>Conclusion</h3><div>Self-reported acute mood or affect may be associated with RR-QoL, lung function, and adjusted all-cause mortality in patients with f-ILD.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100660"},"PeriodicalIF":0.0,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144912881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Joshua Ivare MD, MS , David N. Tryon MD , Adam K. Jacob MD , Timothy B. Curry MD, PhD , Amir Lerman MD
{"title":"Practice Improvement Project: Developing a Platform for a Remote At-Home Preoperative Evaluation for Elective Noncardiac Procedures","authors":"Joshua Ivare MD, MS , David N. Tryon MD , Adam K. Jacob MD , Timothy B. Curry MD, PhD , Amir Lerman MD","doi":"10.1016/j.mayocpiqo.2025.100657","DOIUrl":"10.1016/j.mayocpiqo.2025.100657","url":null,"abstract":"<div><h3>Objective</h3><div>To assess the feasibility, safety, and patient satisfaction associated with a remote cardiac evaluation protocol during a preanesthesia medical evaluation (PAME) before elective noncardiac surgical procedures.</div></div><div><h3>Patients and Methods</h3><div>Eligible patients undergoing elective noncardiac procedures from May 1, 2022 to September 30, 2023 were selected from an anesthesia triage list at a single health care center. Patients received electronic devices for remote blood pressure measurement and 12-lead electrocardiogram collection. Patients either had a telemedicine-based PAME (tPAME) visit or an in-person PAME (iPAME) visit afterward. Patients’ charts were reviewed 30 days after procedure to identify after procedure complications. Patients were asked to provide feedback about their experiences through a digital after procedure satisfaction survey. Comparisons between the tPAME group and the iPAME group were made with χ<sup>2</sup>, Fisher exact, or Mann-Whitney U tests.</div></div><div><h3>Results</h3><div>Of 129 eligible patients, 48 (37.2%) participated in the study. 29 (60.4%) patients had an iPAME visit, and 19 (39.6%) patients had a tPAME visit. There were no major adverse cardiovascular events after a remote cardiac evaluation in the iPAME and the tPAME groups. One (3.4%) patient in the iPAME group developed a deep vein thrombosis and pulmonary embolism after procedure, and 1 (3.4%) patient in the iPAME group had an emergency room visit within 30 days after their procedure. Patients were very satisfied with their experience in the study.</div></div><div><h3>Conclusion</h3><div>These findings support the concept that a remote cardiac evaluation during a PAME before elective noncardiac procedures is feasible, safe, and associated with high patient satisfaction.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100657"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comorbidity Disease Pattern in Japanese Elderly Population: A Network-Based Analysis","authors":"Shuko Nojiri PhD , Wataru Urasaki MSc , Masao Iwagami MD, PhD , Masashi Nagao MD, PhD , Takuya Uematsu MSc , Muneaki Ishijima MD, PhD , Hiroyuki Daida MD, PhD , Yuji Nishizaki MD, PhD","doi":"10.1016/j.mayocpiqo.2025.100646","DOIUrl":"10.1016/j.mayocpiqo.2025.100646","url":null,"abstract":"<div><h3>Objective</h3><div>To clarify the disease pattern for elderly individuals in the general population in Japan with multimorbidity networks based on an analysis of common chronic conditions.</div></div><div><h3>Patients and Methods</h3><div>This study is a population study of disease network analysis in elderly in Japan. We obtained medical records for 4,797,907 elderly patients in Japan (from January 1, 2020 to December 31, 2020) from administrative claim databases. The administrative claim records were transformed for temporal disease occurrence pattern analysis and used to find frequently occurring disease sequences to predict the onset of disease progression.</div></div><div><h3>Results</h3><div>In those aged 75 years and older, circulatory and respiratory diseases gained predominance, while the burden of mental disorders remained substantial across all age groups. In men aged below 75 years, disseminated intravascular coagulation co-occurred frequently with acute myocardial infarction and respiratory failure. In women aged below 75 years, the pairing of vestibular dysfunction and hearing loss exhibited the highest association. For women aged 75 years and older, renal disease pairings, psychiatric comorbidities, and fall-related injuries were dominant. Network analyses reported increasing multimorbidity complexity with age. Respiratory, circulatory, and digestive disease clusters were central across age groups, with psychiatric and fracture-related conditions becoming more prominent in older adults, particularly women. Disease heatmaps further highlighted systemic comorbidity hubs involving pneumonia, iron deficiency anemia, kidney disease, and cardiovascular conditions.</div></div><div><h3>Conclusion</h3><div>In this study, we identified major comorbidity patterns and reported that atherosclerosis, angina pectoris, gastritis, and duodenitis were the most important comorbid diseases in the elderly population in Japan. The identification of distinctive comorbidity profiles from routine clinical data provides insights that may be leveraged to improve diagnosis and identify treatment targets for patients.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100646"},"PeriodicalIF":0.0,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144879947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hee Tae Yu MD, PhD , Laura E. Walker MD , Eunjung Lee PhD , Muhannad Abbasi MBBCh , Samuel Wopperer MD , Gal Tsaban MD, PhD , Kathleen Kopecky MD , Francisco Lopez-Jimenez MD , Paul Friedman MD , Zachi Attia PhD , Jae K. Oh MD
{"title":"An Artificial Intelligence-Enabled Electrocardiogram to Evaluate Patients With Dyspnea in the Emergency Department","authors":"Hee Tae Yu MD, PhD , Laura E. Walker MD , Eunjung Lee PhD , Muhannad Abbasi MBBCh , Samuel Wopperer MD , Gal Tsaban MD, PhD , Kathleen Kopecky MD , Francisco Lopez-Jimenez MD , Paul Friedman MD , Zachi Attia PhD , Jae K. Oh MD","doi":"10.1016/j.mayocpiqo.2025.100652","DOIUrl":"10.1016/j.mayocpiqo.2025.100652","url":null,"abstract":"<div><h3>Objective</h3><div>To evaluate whether an Artificial Intelligence-Enabled Electrocardiogram (AI-ECG) for diastolic function/filling pressure can determine whether dyspnea in emergency department (ED) patients is cardiac in origin.</div></div><div><h3>Patients and Methods</h3><div>We identified 2412 patients aged 18 years or older presented with dyspnea/shortness of breath to the ED who had an ECG performed at the time of evaluation from January 2020 to December 2022. The AI-ECG for determining left ventricular diastolic function to identify the patients with cardiac cause of dyspnea was assessed, using the final diagnosis based on subsequent evaluation.</div></div><div><h3>Results</h3><div>Of the 2412 patients, 966 (40%) were found to have cardiac dyspnea, and the remaining 1446 (60%) were noncardiac. The AI-ECG-estimated diastolic function was divided into 4 groups: 922 (38.2%) were normal, 245 (10.2%) grade 1, 1192 (49.4%) grade 2, and 53 (2.2%) grade 3. The probability of cardiac dyspnea was considerably higher in patients with grade 2 (62.2%±48.5%) and 3 (83%±37.9%) diastolic function compared with normal (14.1%±34.8%) and grade 1 (20.8%±40.7%). The incidence of cardiac dyspnea increased as the probability of increasing filling pressure increased on AI-ECG.</div></div><div><h3>Conclusion</h3><div>Patients often present to the ED with undifferentiated dyspnea. It is important to promptly determine whether the symptoms have cardiac origin. Cardiac dyspnea often reflects elevated left ventricular filling pressures. Artificial intelligence-enhanced 12-lead electrocardiograms can precisely assess diastolic function and filling pressures. Among patients who presented to the ED with dyspnea/shortness of breath, AI-ECG assessing diastolic function strongly distinguished whether the cause was cardiac.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100652"},"PeriodicalIF":0.0,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144879948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jeanne L. Theis PhD , Surendra Dasari PhD , Jason D. Theis BS , Julie A. Vrana PhD , Linda Hasadsri MD, PhD , Joel Fernandez MD , Ellen D. McPhail MD
{"title":"First Reported Case of Dual Hereditary Gelsolin and Transthyretin Wild-Type Cardiac Amyloidosis in a Man in his late 40s","authors":"Jeanne L. Theis PhD , Surendra Dasari PhD , Jason D. Theis BS , Julie A. Vrana PhD , Linda Hasadsri MD, PhD , Joel Fernandez MD , Ellen D. McPhail MD","doi":"10.1016/j.mayocpiqo.2025.100648","DOIUrl":"10.1016/j.mayocpiqo.2025.100648","url":null,"abstract":"<div><div>Amyloidosis is a group of disorders characterized by abnormal deposition of amyloid proteins in various tissues and organs, leading to progressive organ dysfunction. With over 40 precursor proteins linked to amyloid formation, identification of the amyloid type is critical to guide treatment. A man in his late 40s presenting with heart failure was diagnosed with cardiac amyloidosis based on an endomyocardial biopsy. Amyloid typing performed on the heart biopsy at Mayo Clinic Laboratories using differential laser microdissection and shotgun proteomics with mass spectrometry reported gelsolin amyloid (AGel) deposits exclusively in the vasculature and transthyretin amyloid deposits exclusively within the interstitium. Mutational analysis identified a novel p.Y474N in the gelsolin gene, establishing a diagnosis of hereditary AGel amyloidosis. Transthyretin gene mutations were absent, confirming a concurrent diagnosis of acquired transthyretin wild-type amyloidosis. The patient, who had been treated with guideline-directed medical therapy since his initial presentation, was subsequently started on tafamidis, with subsequent improvement of his ejection fraction after 6-7 months. Although rare, 2 different amyloid types may arise in the same anatomic site. Identification of all amyloid types is crucial for optimal patient management. In this case, the co-existence of 2 rare amyloid types (AGel with a novel mutation coupled with ATTRwt in a patient under 50 years of age) in mutually exclusive anatomic compartments in the same cardiac biopsy raises the possibility that an unknown systemic factor may play a role in amyloidogenesis in dual amyloid cases.</div></div>","PeriodicalId":94132,"journal":{"name":"Mayo Clinic proceedings. Innovations, quality & outcomes","volume":"9 5","pages":"Article 100648"},"PeriodicalIF":0.0,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144864405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}