RESUMEN
BACKGROUND: Diagnosis of mitral regurgitation (MR) requires careful evaluation by echocardiography with Doppler imaging. This study presents the development and validation of a fully automated deep learning pipeline for identifying apical 4-chamber view videos with color Doppler echocardiography and detecting clinically significant (moderate or severe) MR from transthoracic echocardiograms. METHODS: A total of 58 614 transthoracic echocardiograms (2 587 538 videos) from Cedars-Sinai Medical Center were used to develop and test an automated pipeline to identify apical 4-chamber view videos with color Doppler across the mitral valve and then assess MR severity. The model was tested internally on a test set of 1800 studies (80 833 videos) from Cedars-Sinai Medical Center and externally evaluated in a geographically distinct cohort of 915 studies (46 890 videos) from Stanford Healthcare. RESULTS: In the held-out Cedars-Sinai Medical Center test set, the view classifier demonstrated an area under the curve (AUC) of 0.998 (0.998-0.999) and correctly identified 3452 of 3539 echocardiography videos as having color Doppler information across the mitral valve (sensitivity of 0.975 [0.968-0.982] and specificity of 0.999 [0.999-0.999] compared with manually curated videos). In the external test cohort from Stanford Healthcare, the view classifier correctly identified 1051 of 1055 manually curated videos with color Doppler information across the mitral valve (sensitivity of 0.996 [0.990-1.000] and specificity of 0.999 [0.999-0.999]). In the Cedars-Sinai Medical Center test cohort, MR moderate or greater in severity was detected with an AUC of 0.916 (0.899-0.932) and severe MR was detected with an AUC of 0.934 (0.913-0.953). In the Stanford Healthcare test cohort, the model detected MR moderate or greater in severity with an AUC of 0.951 (0.924-0.973) and severe MR with an AUC of 0.969 (0.946-0.987). CONCLUSIONS: In this study, a novel automated pipeline for identifying clinically significant MR from full transthoracic echocardiography studies demonstrated excellent performance across large numbers of studies and across multiple institutions. Such an approach has the potential for automated screening and surveillance of MR.
RESUMEN
Purpose: Medical imaging-based machine learning (ML) for computer-aided diagnosis of in vivo lesions consists of two basic components or modules of (i) feature extraction from non-invasively acquired medical images and (ii) feature classification for prediction of malignancy of lesions detected or localized in the medical images. This study investigates their individual performances for diagnosis of low-dose computed tomography (CT) screening-detected lesions of pulmonary nodules and colorectal polyps. Approach: Three feature extraction methods were investigated. One uses the mathematical descriptor of gray-level co-occurrence image texture measure to extract the Haralick image texture features (HFs). One uses the convolutional neural network (CNN) architecture to extract deep learning (DL) image abstractive features (DFs). The third one uses the interactions between lesion tissues and X-ray energy of CT to extract tissue-energy specific characteristic features (TFs). All the above three categories of extracted features were classified by the random forest (RF) classifier with comparison to the DL-CNN method, which reads the images, extracts the DFs, and classifies the DFs in an end-to-end manner. The ML diagnosis of lesions or prediction of lesion malignancy was measured by the area under the receiver operating characteristic curve (AUC). Three lesion image datasets were used. The lesions' tissue pathological reports were used as the learning labels. Results: Experiments on the three datasets produced AUC values of 0.724 to 0.878 for the HFs, 0.652 to 0.965 for the DFs, and 0.985 to 0.996 for the TFs, compared to the DL-CNN of 0.694 to 0.964. These experimental outcomes indicate that the RF classifier performed comparably to the DL-CNN classification module and the extraction of tissue-energy specific characteristic features dramatically improved AUC value. Conclusions: The feature extraction module is more important than the feature classification module. Extraction of tissue-energy specific characteristic features is more important than extraction of image abstractive and characteristic features.
RESUMEN
Background and Aims: Diagnosis of tricuspid regurgitation (TR) requires careful expert evaluation. This study developed an automated deep learning pipeline for assessing TR from transthoracic echocardiography. Methods: An automated deep learning workflow was developed using 47,312 studies (2,079,898 videos) from Cedars-Sinai Medical Center (CSMC) between 2011 and 2021. The pipeline was tested on a temporally distinct test set of 2,462 studies (108,138 videos) obtained in 2022 at CSMC and a geographically distinct cohort of 5,549 studies (278,377 videos) from Stanford Healthcare (SHC). Results: In the CSMC test dataset, the view classifier demonstrated an AUC of 1.000 (0.999 - 1.000) and identified at least one A4C video with colour Doppler across the tricuspid valve in 2,410 of 2,462 studies with a sensitivity of 0.975 (0.968-0.982) and a specificity of 1.000 (1.00-1.000). In the CSMC test cohort, moderate-or-severe TR was detected with an AUC of 0.928 (0.913 - 0.943) and severe TR was detected with an AUC of 0.956 (0.940 - 0.969). In the SHC cohort, the view classifier correctly identified at least one TR colour Doppler video in 5,268 of the 5,549 studies, resulting in an AUC of 0.999 (0.998 - 0.999), a sensitivity of 0.949 (0.944 - 0.955) and specificity of 0.999 (0.999 - 0.999). The AI model detected moderate-or-severe TR with an AUC of 0.951 (0.938 - 0.962) and severe TR with an AUC of 0.980 (0.966 - 0.988). Conclusions: We developed an automated pipeline to identify clinically significant TR with excellent performance. This approach carries potential for automated TR detection and stratification for surveillance and screening. Key Question: Can an automated deep learning model assess tricuspid regurgitation severity from echocardiography? Key Finding: We developed and validated an automated tricuspid regurgitation detection algorithm pipeline across two healthcare systems with high volume echocardiography labs. The algorithm correctly identifies apical-4-chamber view videos with colour Doppler across the tricuspid valve and grades clinically significant TR with strong agreement to expert clinical readers. Take Home message: A deep learning pipeline could automate TR screening, facilitating reproducible accurate assessment of TR severity, allowing rapid triage or re-review and expand access in low-resource or primary care settings.
RESUMEN
Conversion disorder-called functional neurological symptom disorder in the DSM-5-has roots that trace back to antiquity. The term conversion, originating from psychoanalysis, signifies the appearance of physical symptoms as an effort to resolve or convey unconscious and distressing intrapsychic conflicts- "converting" them from manifesting in the mind to manifesting in the body. Despite efforts made in elucidating the neurobiological etiologies of functional neurological symptom disorder, a psychodynamic lens remains indispensable in understanding the patient. This article presents two patients who developed functional neurological symptom disorder, one after a COVID-19 vaccination and one in the context of long COVID. A discussion follows on the intrapersonal, interpersonal, and systemic etiological factors that predispose, precipitate, and perpetuate COVID-related functional neurological symptom disorder. We elaborate on psychodynamic psychological processes and conflicts that may unfold between patients with COVID-related functional neurological symptom disorder and their health care providers. We also share suggestions on how a consultation-liaison psychiatry team may offer support to the primary treating team to facilitate a therapeutic space within which patients with COVID-related functional neurological symptom disorder may recover.
Asunto(s)
COVID-19 , Adulto , Femenino , Humanos , Persona de Mediana Edad , Trastornos de Conversión/psicología , COVID-19/psicología , Vacunas contra la COVID-19 , SARS-CoV-2RESUMEN
BACKGROUND: Echocardiographic strain measurements require extensive operator experience and have significant intervendor variability. Creating an automated, open-source, vendor-agnostic method to retrospectively measure global longitudinal strain (GLS) from standard echocardiography B-mode images would greatly improve post hoc research applications and may streamline patient analyses. OBJECTIVES: This study was seeking to develop an automated deep learning strain (DLS) analysis pipeline and validate its performance across multiple applications and populations. METHODS: Interobserver/-vendor variation of traditional GLS, and simulated effects of variation in contour on speckle-tracking measurements were assessed. The DLS pipeline was designed to take semantic segmentation results from EchoNet-Dynamic and derive longitudinal strain by calculating change in the length of the left ventricular endocardial contour. DLS was evaluated for agreement with GLS on a large external dataset and applied across a range of conditions that result in cardiac hypertrophy. RESULTS: In patients scanned by 2 sonographers using 2 vendors, GLS had an intraclass correlation of 0.29 (95% CI: -0.01 to 0.53, P = 0.03) between vendor measurements and 0.63 (95% CI: 0.48-0.74, P < 0.001) between sonographers. With minor changes in initial input contour, step-wise pixel shifts resulted in a mean absolute error of 3.48% and proportional strain difference of 13.52% by a 6-pixel shift. In external validation, DLS maintained moderate agreement with 2-dimensional GLS (intraclass correlation coefficient [ICC]: 0.56, P = 0.002) with a bias of -3.31% (limits of agreement: -11.65% to 5.02%). The DLS method showed differences (P < 0.0001) between populations with cardiac hypertrophy and had moderate agreement in a patient population of advanced cardiac amyloidosis: ICC was 0.64 (95% CI: 0.53-0.72), P < 0.001, with a bias of 0.57%, limits of agreement of -4.87% to 6.01% vs 2-dimensional GLS. CONCLUSIONS: The open-source DLS provides lower variation than human measurements and similar quantitative results. The method is rapid, consistent, vendor-agnostic, publicly released, and applicable across a wide range of imaging qualities.
Asunto(s)
Aprendizaje Profundo , Ecocardiografía , Interpretación de Imagen Asistida por Computador , Variaciones Dependientes del Observador , Valor Predictivo de las Pruebas , Función Ventricular Izquierda , Humanos , Reproducibilidad de los Resultados , Masculino , Estudios Retrospectivos , Femenino , Persona de Mediana Edad , Contracción Miocárdica , Fenómenos Biomecánicos , Anciano , AutomatizaciónRESUMEN
Social support, as perceived and experienced within one's social network, has been associated with greater well-being and favorable health outcomes. The transition to college marks a critical time in which social support not only strengthens interpersonal bonds, but also may help an individual discover and utilize various coping strategies to lower risks associated with negative emotions, which may result in better health and well-being. In the present study, we collected data from a large sample of undergraduate students (N = 376) and conducted preregistered analyses to examine links between students' perceived social support in residential college communities, patterns of emotion regulation strategy use, and multiple indicators of health and well-being. Overall, we found partial support for our hypotheses, with some associations between social support and patterns of emotion regulation strategy use, as well as associations between strategy use and health indicators. All results held when adjusting for participants' age and gender. Taken together, the present findings revealed reliable links between social network indicators, emotion regulation strategy use, and health. Future research can extend these findings by observing how these relationships unfold over time, to better understand how people manage their emotions by drawing on their personal networks. (PsycInfo Database Record (c) 2024 APA, all rights reserved).
Asunto(s)
Regulación Emocional , Humanos , Regulación Emocional/fisiología , Emociones/fisiología , Apoyo Social , Estudiantes/psicología , Red SocialRESUMEN
A miniature optical-sectioning fluorescence microscope with high sensitivity and resolution would enable non-invasive and real-time tissue inspection, with potential use cases including early disease detection and intraoperative guidance. Previously, we developed a miniature MEMS-based dual-axis confocal (DAC) microscope that enabled video-rate optically sectioned in vivo microscopy of human tissues. However, the device's clinical utility was limited due to a small field of view, a non-adjustable working distance, and a lack of a sterilization strategy. In our latest design, we have made improvements to achieve a 2x increase in the field of view (600 × 300 µm) and an adjustable working distance range of 150 µm over a wide range of excitation/emission wavelengths (488-750â nm), all while maintaining a high frame rate of 15 frames per second (fps). Furthermore, the device is designed to image through a disposable sterile plastic drape for convenient clinical use. We rigorously characterize the performance of the device and show example images of ex vivo tissues to demonstrate the optical performance of our new design, including fixed mouse skin and human prostate, as well as fresh mouse kidney, mouse intestine, and human head and neck surgical specimens with corresponding H&E histology. These improvements will facilitate clinical testing and translation.
RESUMEN
Substrate degradation by the ubiquitin proteasome system (UPS) in specific membrane compartments remains elusive. Here, we show that the interplay of two lipid modifications and PDE6δ regulates compartmental substrate targeting via the SCFFBXL2. FBXL2 is palmitoylated in a prenylation-dependent manner on cysteines 417 and 419 juxtaposed to the CaaX motif. Palmitoylation/depalmitoylation regulates its subcellular trafficking for substrate engagement and degradation. To control its subcellular distribution, lipid-modified FBXL2 interacts with PDE6δ. Perturbing the equilibrium between FBXL2 and PDE6δ disrupts the delivery of FBXL2 to all membrane compartments, whereas depalmitoylated FBXL2 is enriched on the endoplasmic reticulum (ER). Depalmitoylated FBXL2(C417S/C419S) promotes the degradation of IP3R3 at the ER, inhibits IP3R3-dependent mitochondrial calcium overload, and counteracts calcium-dependent cell death upon oxidative stress. In contrast, disrupting the PDE6δ-FBXL2 equilibrium has the opposite effect. These findings describe a mechanism underlying spatially-restricted substrate degradation and suggest that inhibition of FBXL2 palmitoylation and/or binding to PDE6δ may offer therapeutic benefits.
Asunto(s)
Proteínas F-Box , Proteínas F-Box/metabolismo , Calcio/metabolismo , Lipoilación , Ubiquitinación , LípidosRESUMEN
BACKGROUND: Reference change value (RCV) is used to assess the significance of the difference between two measurements after accounting for pre-analytic, analytic, and within-subject variability. The objective of the current study was to define the RCV for global longitudinal strain (GLS) using different semi-automated software in standard clinical practice. METHODS: Using a test-retest study design, we quantified the median coefficient of variation (CV) for GLS using AutoStrain and Automated Cardiac Motion Quantification (aCMQ) by Philips. Triplane left-ventricular ejection fraction (LVEF) was measured for comparison. Multivariable regression analysis was performed to determine factors influencing test-retest CV including image quality and the presence of segmental wall motion abnormalities (WMA). RCV was reported using a standard formula assuming two standard deviations for repeated measurements; results were also translated into Bayesian probability. Total measurement variation was described in terms of its three different components: pre-analytic (acquisition), analytic (measuring variation), and within-subject (biological) variation. RESULT: Of the 44 individuals who were screened, 41 had adequate quality for strain quantification. The mean age of the cohort was 56.4 ± 16.8 years, 41% female, LVEF was 55.8 ± 9.8% and the median and interquartile range for LV GLS was -17.2 [-19.3 to -14.8]%. Autostrain was more time efficient (80% less analysis time) and had a lower total median CV than aCMQ (CV = 7.4% vs. 17.6%, p < .001). The total CV was higher in patients with WMA (6.4% vs. 13.2%, p = .035). In non-segmental disease, the CV translates to a RCV of 15% (corresponding to a probability of real change of 80%). Assuming a within-subject variability of 4.0%, the component analysis identified that inter-reader variability accounts for 3.7% of the CV, while acquisition variability accounts for 4.0%. CONCLUSION: Using test-retest analysis and CVs, we find that an RCV of 15% for GLS represents an optimistic estimate in routine clinical practice. Based on our results, a higher RCV of 17%-21% is needed in order to provide a high probability of clinically meaningful change in GLS in all comers. The methodology presented here for determining measurement reproducibility and RCVs is easily translatable into clinical practice for any imaging parameter.
Asunto(s)
Tensión Longitudinal Global , Función Ventricular Izquierda , Humanos , Femenino , Adulto , Persona de Mediana Edad , Anciano , Masculino , Volumen Sistólico , Teorema de Bayes , Reproducibilidad de los ResultadosRESUMEN
Importance: The risk of adverse events from ascending thoracic aorta aneurysm (TAA) is poorly understood but drives clinical decision-making. Objective: To evaluate the association of TAA size with outcomes in nonsyndromic patients in a large non-referral-based health care delivery system. Design, Setting, and Participants: The Kaiser Permanente Thoracic Aortic Aneurysm (KP-TAA) cohort study was a retrospective cohort study at Kaiser Permanente Northern California, a fully integrated health care delivery system insuring and providing care for more than 4.5 million persons. Nonsyndromic patients from a regional TAA safety net tracking system were included. Imaging data including maximum TAA size were merged with electronic health record (EHR) and comprehensive death data to obtain demographic characteristics, comorbidities, medications, laboratory values, vital signs, and subsequent outcomes. Unadjusted rates were calculated and the association of TAA size with outcomes was evaluated in multivariable competing risk models that categorized TAA size as a baseline and time-updated variable and accounted for potential confounders. Data were analyzed from January 2018 to August 2021. Exposures: TAA size. Main Outcomes and Measures: Aortic dissection (AD), all-cause death, and elective aortic surgery. Results: Of 6372 patients with TAA identified between 2000 and 2016 (mean [SD] age, 68.6 [13.0] years; 2050 female individuals [32.2%] and 4322 male individuals [67.8%]), mean (SD) initial TAA size was 4.4 (0.5) cm (828 individuals [13.0% of cohort] had initial TAA size 5.0 cm or larger and 280 [4.4%] 5.5 cm or larger). Rates of AD were low across a mean (SD) 3.7 (2.5) years of follow-up (44 individuals [0.7% of cohort]; incidence 0.22 events per 100 person-years). Larger initial aortic size was associated with higher risk of AD and all-cause death in multivariable models, with an inflection point in risk at 6.0 cm. Estimated adjusted risks of AD within 5 years were 0.3% (95% CI, 0.3-0.7), 0.6% (95% CI, 0.4-1.3), 1.5% (95% CI, 1.2-3.9), 3.6% (95% CI, 1.8-12.8), and 10.5% (95% CI, 2.7-44.3) in patients with TAA size of 4.0 to 4.4 cm, 4.5 to 4.9 cm, 5.0 to 5.4 cm, 5.5 to 5.9 cm, and 6.0 cm or larger, respectively, in time-updated models. Rates of the composite outcome of AD and all-cause death were higher than for AD alone, but a similar inflection point for increased risk was observed at 6.0 cm. Conclusions and Relevance: In a large sociodemographically diverse cohort of patients with TAA, absolute risk of aortic dissection was low but increased with larger aortic sizes after adjustment for potential confounders and competing risks. Our data support current consensus guidelines recommending prophylactic surgery in nonsyndromic individuals with TAA at a 5.5-cm threshold.
Asunto(s)
Aneurisma de la Aorta Torácica , Disección Aórtica , Humanos , Masculino , Femenino , Anciano , Aneurisma de la Aorta Torácica/epidemiología , Aneurisma de la Aorta Torácica/cirugía , Estudios Retrospectivos , Estudios de Cohortes , Disección Aórtica/diagnóstico , IncidenciaRESUMEN
The ubiquitin proteasome system (UPS) is a proteolytic machinery for the degradation of protein substrates that are post-translationally conjugated with ubiquitin polymers through the enzymatic action of ubiquitin ligases, in a process termed ubiquitylation. Ubiquitylation of substrates precedes their proteolysis via proteasomes, a hierarchical feature of UPS. E3-ubiquitin ligases recruit protein substrates providing specificity for ubiquitylation. Innate and adaptive immune system networks are regulated by ubiquitylation and substrate degradation via E3-ligases/UPS. Deregulation of E3-ligases/UPS components in immune cells is involved in the development of lymphomas, neurodevelopmental abnormalities, and cancers. Targeting E3-ligases for therapeutic intervention provides opportunities to mitigate the unintended broad effects of 26S proteasome inhibition. Recently, bifunctional moieties such as PROTACs and molecular glues have been developed to re-purpose E3-ligases for targeted degradation of unwanted aberrant proteins, with a potential for clinical use. Here, we summarize the involvement of E3-ligases/UPS components in immune-related diseases with perspectives.
Asunto(s)
Complejo de la Endopetidasa Proteasomal , Ubiquitina , Humanos , Ubiquitina/metabolismo , Complejo de la Endopetidasa Proteasomal/metabolismo , Ubiquitina-Proteína Ligasas/metabolismo , Proteolisis , Proteínas/metabolismoRESUMEN
Objective: Aortic root (AoR) size remains an imperfect predictor of rate of aortic dilation in Marfan syndrome (MFS). Indicators of vascular phenotype such as aortic stiffness have been proposed as additional predictors. In this study we assessed the rate of AoR dilation and stiffness in adult patients with MFS. Methods: We performed a retrospective chart review. We included adult patients with MFS (aged 20-40 years) with at least 2 local echocardiograms 6 months apart (no aortic surgery in-between). A blinded observer analyzed the echocardiograms. AoR dilation rate and stiffness were calculated. Results: Thirty-two patients (53% women; median age, 21.1; interquartile range [IQR], 19-24 years at first echocardiogram) were included. AoR dilation rate in the entire cohort was 0 to 8 mm/year (median, 0.465; IQR, 0.23-1.45 mm/year). Multiple linear regression analysis showed that baseline AoR stiffness was associated with AoR dilation rate (ß = 0.0004; P < .001 for elastic modulus), whereas baseline age and baseline AoR dimension were not. Eighteen of these 32 patients (56%) eventually had AoR surgery (Sx) and 14 did not have surgery (NSx). At baseline, Sx and NSx patients were similar in age. AoR dimension was larger (Sx, 4.27 cm; IQR, 4.05-4.49 cm vs NSx, 3.73 cm; IQR, 3.37-4.09 cm; P = .011) and AoR stiffness was higher in Sx patients (beta stiffness index: median, 23.2; IQR, 17.8-28.6 vs median, 15.6; IQR, 11.6-19.7; P = .024). AoR dilation rate was greater in Sx patients, independent of baseline AoR dimension (1.63 ± 0.41 mm/year vs 0.38 ± 0.08 mm/year; P = .01). Conclusions: Our results showed that AoR dilation rate varies among adult patients with MFS and is associated with baseline AoR stiffness, measured by echocardiography. Further studies are warranted to determine how aortic stiffness can be implemented clinically to refine management in patients with MFS.
RESUMEN
Familial dilated cardiomyopathy (DCM) is among the most prevalent forms of inherited heart disease. Here, two human-induced pluripotent stem cell (iPSC) lines were generated from peripheral blood mononuclear cells (PBMCs) from DCM patients carrying different mutations in the phospholamban encoding-gene (PLN). Both iPSC lines exhibited normal morphology, karyotype, pluripotency marker expression, and differentiation into the three germ layers. These patient-specific iPSC lines serve as valuable in vitro models for DCM pathology caused by PLN mutations.
Asunto(s)
Cardiomiopatía Dilatada , Células Madre Pluripotentes Inducidas , Proteínas de Unión al Calcio , Cardiomiopatía Dilatada/genética , Técnicas de Cultivo de Célula , Células Cultivadas , Heterocigoto , Humanos , Células Madre Pluripotentes Inducidas/metabolismo , Leucocitos Mononucleares/metabolismo , Mutación/genéticaRESUMEN
The assessment of the duration of pharmacological prescriptions is an important phase in pharmacoepidemiologic studies aiming to investigate persistence, effectiveness or safety of treatments. The Sessa Empirical Estimator (SEE) is a new data-driven method which uses k-means algorithm for computing the duration of pharmacological prescriptions in secondary data sources when this information is missing or incomplete. The SEE was used to compute durations of exposure to pharmacological treatments where simulated and real-world data were used to assess its properties comparing the exposure status extrapolated with the method with the "true" exposure status available in the simulated and real-world data. Finally, the SEE was also compared to a Researcher-Defined Duration (RDD) method. When using simulated data, the SEE showed accuracy of 96% and sensitivity of 96%, while when using real-world data, the method showed sensitivity ranging from 78.0 (nortriptyline) to 95.1% (propafenone). When compared to the RDD, the method had a lower median sensitivity of 2.29% (interquartile range 1.21-4.11%). The SEE showed good properties and may represent a promising tool to assess exposure status when information on treatment duration is not available.
Asunto(s)
Almacenamiento y Recuperación de la Información , Prescripciones , Recolección de DatosRESUMEN
BACKGROUND: We aimed at evaluating adverse drug reactions during the post-marketing phase with erenumab as the suspected/interacting drug in Eudravigilance, with the final goal of investigating the consistency of the disproportionality signals (DS) for erenumab in Eudravigilance and the American Food and Drug Administration Adverse Event Reporting System (FDA FAERS) and undetected DS from Eudravigilance. RESEARCH DESIGN AND METHODS: Eudravigilance was screened in the period from October 2019 to October 2020. Disproportionality measure was performed using the Reporting Odds Ratio (ROR) according to the guidelines by the European Medicine Agency and using sumatriptan as the control group. RESULTS: 3381 cases were reported in the study period. Forty DS were identified both in Eudravigilance and FAERS. Sixteen DS were not identified in FAERS, 10 DS were found to have biological probability and six DS were considered false-positive and potentially related to confounding by indication. The three system organ classes with the highest proportion of adverse events were general disorders and administration site conditions (16.12%), nervous system disorders (15.95%), and gastrointestinal disorders (13.59%). CONCLUSIONS: Adverse events reports were mostly reported as non-serious. Co-analysis of multiple spontaneous reported databases unveiled undetected DS for erenumab in individual databases. Future studies should be conducted to confirm the associations and potential clinical implications.
Asunto(s)
Sistemas de Registro de Reacción Adversa a Medicamentos , Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos , Anticuerpos Monoclonales Humanizados , Bases de Datos Factuales , Efectos Colaterales y Reacciones Adversas Relacionados con Medicamentos/epidemiología , Humanos , Mercadotecnía , Sumatriptán , Estados Unidos , United States Food and Drug AdministrationRESUMEN
IMPORTANCE: Early detection and characterization of increased left ventricular (LV) wall thickness can markedly impact patient care but is limited by under-recognition of hypertrophy, measurement error and variability, and difficulty differentiating causes of increased wall thickness, such as hypertrophy, cardiomyopathy, and cardiac amyloidosis. OBJECTIVE: To assess the accuracy of a deep learning workflow in quantifying ventricular hypertrophy and predicting the cause of increased LV wall thickness. DESIGN, SETTINGS, AND PARTICIPANTS: This cohort study included physician-curated cohorts from the Stanford Amyloid Center and Cedars-Sinai Medical Center (CSMC) Advanced Heart Disease Clinic for cardiac amyloidosis and the Stanford Center for Inherited Cardiovascular Disease and the CSMC Hypertrophic Cardiomyopathy Clinic for hypertrophic cardiomyopathy from January 1, 2008, to December 31, 2020. The deep learning algorithm was trained and tested on retrospectively obtained independent echocardiogram videos from Stanford Healthcare, CSMC, and the Unity Imaging Collaborative. MAIN OUTCOMES AND MEASURES: The main outcome was the accuracy of the deep learning algorithm in measuring left ventricular dimensions and identifying patients with increased LV wall thickness diagnosed with hypertrophic cardiomyopathy and cardiac amyloidosis. RESULTS: The study included 23â¯745 patients: 12â¯001 from Stanford Health Care (6509 [54.2%] female; mean [SD] age, 61.6 [17.4] years) and 1309 from CSMC (808 [61.7%] female; mean [SD] age, 62.8 [17.2] years) with parasternal long-axis videos and 8084 from Stanford Health Care (4201 [54.0%] female; mean [SD] age, 69.1 [16.8] years) and 2351 from CSMS (6509 [54.2%] female; mean [SD] age, 69.6 [14.7] years) with apical 4-chamber videos. The deep learning algorithm accurately measured intraventricular wall thickness (mean absolute error [MAE], 1.2 mm; 95% CI, 1.1-1.3 mm), LV diameter (MAE, 2.4 mm; 95% CI, 2.2-2.6 mm), and posterior wall thickness (MAE, 1.4 mm; 95% CI, 1.2-1.5 mm) and classified cardiac amyloidosis (area under the curve [AUC], 0.83) and hypertrophic cardiomyopathy (AUC, 0.98) separately from other causes of LV hypertrophy. In external data sets from independent domestic and international health care systems, the deep learning algorithm accurately quantified ventricular parameters (domestic: R2, 0.96; international: R2, 0.90). For the domestic data set, the MAE was 1.7 mm (95% CI, 1.6-1.8 mm) for intraventricular septum thickness, 3.8 mm (95% CI, 3.5-4.0 mm) for LV internal dimension, and 1.8 mm (95% CI, 1.7-2.0 mm) for LV posterior wall thickness. For the international data set, the MAE was 1.7 mm (95% CI, 1.5-2.0 mm) for intraventricular septum thickness, 2.9 mm (95% CI, 2.4-3.3 mm) for LV internal dimension, and 2.3 mm (95% CI, 1.9-2.7 mm) for LV posterior wall thickness. The deep learning algorithm accurately detected cardiac amyloidosis (AUC, 0.79) and hypertrophic cardiomyopathy (AUC, 0.89) in the domestic external validation site. CONCLUSIONS AND RELEVANCE: In this cohort study, the deep learning model accurately identified subtle changes in LV wall geometric measurements and the causes of hypertrophy. Unlike with human experts, the deep learning workflow is fully automated, allowing for reproducible, precise measurements, and may provide a foundation for precision diagnosis of cardiac hypertrophy.