Pablo Amador Sanchez

All Publications

• Multimodal deep learning enhances diagnostic precision in left ventricular hypertrophy. European heart journal. Digital health Soto, J. T., Weston Hughes, J., Sanchez, P. A., Perez, M., Ouyang, D., Ashley, E. A. 2022; 3 (3): 380-389

  Abstract

  Aims: Determining the aetiology of left ventricular hypertrophy (LVH) can be challenging due to the similarity in clinical presentation and cardiac morphological features of diverse causes of disease. In particular, distinguishing individuals with hypertrophic cardiomyopathy (HCM) from the much larger set of individuals with manifest or occult hypertension (HTN) is of major importance for family screening and the prevention of sudden death. We hypothesized that an artificial intelligence method based joint interpretation of 12-lead electrocardiograms and echocardiogram videos could augment physician interpretation.Methods and results: We chose not to train on proximate data labels such as physician over-reads of ECGs or echocardiograms but instead took advantage of electronic health record derived clinical blood pressure measurements and diagnostic consensus (often including molecular testing) among physicians in an HCM centre of excellence. Using more than 18000 combined instances of electrocardiograms and echocardiograms from 2728 patients, we developed LVH-fusion. On held-out test data, LVH-fusion achieved an F1-score of 0.71 in predicting HCM, and 0.96 in predicting HTN. In head-to-head comparison with human readers LVH-fusion had higher sensitivity and specificity rates than its human counterparts. Finally, we use explainability techniques to investigate local and global features that positively and negatively impact LVH-fusion prediction estimates providing confirmation from unsupervised analysis the diagnostic power of lateral T-wave inversion on the ECG and proximal septal hypertrophy on the echocardiogram for HCM.Conclusion: These results show that deep learning can provide effective physician augmentation in the face of a common diagnostic dilemma with far reaching implications for the prevention of sudden cardiac death.

  View details for DOI 10.1093/ehjdh/ztac033

  View details for PubMedID 36712167

• Training in Critical Care Cardiology Within Critical Care Medicine Fellowship: A Novel Pathway. Journal of the American College of Cardiology O'Brien, C. G., Barnett, C. F., Dudzinski, D. M., Sanchez, P. A., Katz, J. N., Harold, J. G., Hennessey, E. K., Mohabir, P. K. 2022; 79 (6): 609-613

  View details for DOI 10.1016/j.jacc.2021.12.009

  View details for PubMedID 35144752

• Editor's Choice-Prospective registry of cardiac critical illness in a modern tertiary care Cardiac Intensive Care Unit. European heart journal. Acute cardiovascular care Watson, R. A., Bohula, E. A., Gilliland, T. C., Sanchez, P. A., Berg, D. D., Morrow, D. A. 2019; 8 (8): 755-761

  Abstract

  The changing landscape of care in the Cardiac Intensive Care Unit (CICU) has prompted efforts to redesign the structure and organization of advanced CICUs. Few studies have quantitatively characterized current demographics, diagnoses, and outcomes in the contemporary CICU.We evaluated patients in a prospective observational database, created to support quality improvement and clinical care redesign in an AHA Level 1 (advanced) CICU at Brigham and Women's Hospital, Boston, MA, USA. All consecutive patients (N=2193) admitted from 1 January 2015 to 31 December 2017 were included at the time of admission to the CICU.The median age was 65 years (43% >70 years) and 44% of patients were women. Non-cardiovascular comorbidities were common, including chronic kidney disease (27%), pulmonary disease (22%), and active cancer (13%). Only 7% of CICU admissions were primarily for an acute coronary syndrome, which was the seventh most common individual diagnosis. The top three reasons for admission to the CICU were shock/hypotension (26%), cardiopulmonary arrest (11%), or primary arrhythmia without arrest (9%). Respiratory failure was a primary or major secondary reason for triage to the CICU in 17%. In-hospital mortality was 17.6%.In a tertiary, academic, advanced CICU, patients are elderly with a high burden of non-cardiovascular comorbid conditions. Care has shifted from ACS toward predominantly shock and cardiac arrest, as well as non-ischemic conditions, and the mortality of these conditions is high. These data may be useful to guide cardiac critical care redesign.

  View details for DOI 10.1177/2048872618789053

  View details for PubMedID 30033736

• Human Induced Pluripotent Stem Cell-Derived Cardiomyocyte Patch in Rats With Heart Failure. The Annals of thoracic surgery Lancaster, J. J., Sanchez, P., Repetti, G. G., Juneman, E., Pandey, A. C., Chinyere, I. R., Moukabary, T., LaHood, N., Daugherty, S. L., Goldman, S. 2019; 108 (4): 1169-1177

  Abstract

  To treat chronic heart failure (CHF), we developed a robust, easy to handle bioabsorbable tissue-engineered patch embedded with human neonatal fibroblasts and human induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CMs). This patch was implanted on the epicardial surface of the heart covering the previously infarcted tissue.Sprague-Dawley rats (6-8 weeks old) underwent sham surgery (n = 12) or left coronary artery ligation (n = 45). CHF rats were randomized 3 weeks after ligation to CHF control with sham thoracotomy (n = 21), or a fibroblasts/hiPSC-CMs patch (n = 24) was implanted. All sham surgery rats also underwent a sham thoracotomy. At 3 weeks after randomization, hemodynamics, echocardiography, electrophysiologic, and cell survival studies were performed.Patch-treated rats had decreased (P < .05) left ventricular-end diastolic pressure and the time constant of left ventricular relaxation (Tau), increased anterior wall thickness in diastole, and improved echocardiography-derived indices of diastolic function (E/e' [ratio of early peak flow velocity to early peak LV velocity] and e'/a' [ratio of early to late peak left ventricular velocity]). All rats remained in normal sinus rhythm, with no dysrhythmias. Rats treated with the patch showed improved electrical activity. Transplanted hiPSC-CMs were present at 7 days but not detected at 21 days after implantation. The patch increased (P < .05) gene expression of vascular endothelial growth factor, angiopoietin 1, gap junction α-1 protein (connexin 43), β-myosin heavy 7, and insulin growth factor-1 expression in the infarcted heart.Epicardial implantation of a fibroblasts/hiPSC-CMs patch electrically enhanced conduction, lowered left ventricular end-diastolic pressure, and improved diastolic function in rats with CHF. These changes were associated with increases in cytokine expression.

  View details for DOI 10.1016/j.athoracsur.2019.03.099

  View details for PubMedID 31075250

• Identification of Racial Inequities in Access to Specialized Inpatient Heart Failure Care at an Academic Medical Center. Circulation. Heart failure Eberly, L. A., Richterman, A. n., Beckett, A. G., Wispelwey, B. n., Marsh, R. H., Cleveland Manchanda, E. C., Chang, C. Y., Glynn, R. J., Brooks, K. C., Boxer, R. n., Kakoza, R. n., Goldsmith, J. n., Loscalzo, J. n., Morse, M. n., Lewis, E. F., Abel, S. n., Adams, A. n., Anaya, J. n., Andrews, E. H., Atkinson, B. n., Avutu, V. n., Bachorik, A. n., Badri, O. n., Bailey, M. n., Baird, K. n., Bakshi, S. n., Balaban, D. n., Barshop, K. n., Baumrin, E. n., Bayomy, O. n., Beamesderfer, J. n., Becker, N. n., Berg, D. D., Berman, A. N., Blum, S. M., Boardman, A. P., Boden, K. n., Bonacci, R. A., Brown, S. n., Campbell, K. n., Case, S. n., Cetrone, E. n., Charrow, A. n., Chiang, D. n., Clark, D. n., Cohen, A. J., Cooper, A. n., Cordova, T. n., Cuneo, C. N., de Feria, A. A., Deffenbacher, K. n., DeFilippis, E. M., DeGregorio, G. n., Deutsch, A. J., Diephuis, B. n., Divakaran, S. n., Dorschner, P. n., Downing, N. n., Drescher, C. n., D'Silva, K. M., Dunbar, P. n., Duong, D. n., Earp, S. n., Eckhardt, C. n., Elman, S. A., England, R. n., Everett, K. n., Fedotova, N. n., Feingold-Link, T. n., Ferreira, M. n., Fisher, H. n., Foo, P. n., Foote, M. n., Franco, I. n., Gilliland, T. n., Greb, J. n., Greco, K. n., Grewal, S. n., Grin, B. n., Growdon, M. E., Guercio, B. n., Hahn, C. K., Hasselfeld, B. n., Haydu, E. J., Hermes, Z. n., Hildick-Smith, G. n., Holcomb, Z. n., Holroyd, K. n., Horton, L. n., Huang, G. n., Jablonski, S. n., Jacobs, D. n., Jain, N. n., Japa, S. n., Joseph, R. n., Kalashnikova, M. n., Kalwani, N. n., Kang, D. n., Karan, A. n., Katz, J. T., Kellner, D. n., Kidia, K. n., Kim, J. H., Knowles, S. M., Kolbe, L. n., Kore, I. n., Koullias, Y. n., Kuye, I. n., Lang, J. n., Lawlor, M. n., Lechner, M. G., Lee, K. n., Lee, S. n., Lee, Z. n., Limaye, N. n., Lin-Beckford, S. n., Lipsyc, M. n., Little, J. n., Loewenthal, J. n., Logaraj, R. n., Lopez, D. M., Loriaux, D. n., Lu, Y. n., Ma, K. n., Marukian, N. n., Matias, W. n., Mayers, J. R., McConnell, I. n., McLaughlin, M. n., Meade, C. n., Meador, C. n., Mehta, A. n., Messenger, E. n., Michaelidis, C. n., Mirsky, J. n., Mitten, E. n., Mueller, A. n., Mullur, J. n., Munir, A. n., Murphy, E. n., Nagami, E. n., Natarajan, A. n., Nsahlai, M. n., Nze, C. n., Okwara, N. n., Olds, P. n., Paez, R. n., Pardo, M. n., Patel, S. n., Petersen, A. n., Phelan, L. n., Pimenta, E. n., Pipilas, D. n., Plovanich, M. n., Pong, D. n., Powers, B. W., Rao, A. n., Ramirez Batlle, H. n., Ramsis, M. n., Reichardt, A. n., Reiger, S. n., Rengarajan, M. n., Rico, S. n., Rome, B. N., Rosales, R. n., Rotenstein, L. n., Roy, A. n., Royston, S. n., Rozansky, H. n., Rudder, M. n., Ryan, C. E., Salgado, S. n., Sanchez, P. n., Schulte, J. n., Sekar, A. n., Semenkovich, N. n., Shannon, E. n., Shaw, N. n., Shorten, A. B., Shrauner, W. n., Sinnenberg, L. n., Smithy, J. W., Snyder, G. n., Sreekrishnan, A. n., Stabenau, H. n., Stavrou, E. n., Stergachis, A. n., Stern, R. n., Stone, A. n., Tabrizi, S. n., Tanyos, S. n., Thomas, C. n., Thun, H. n., Torres-Lockhart, K. n., Tran, A. n., Treasure, C. n., Tsai, F. D., Tsaur, S. n., Tschirhart, E. n., Tuwatananurak, J. n., Venkateswaran, R. V., Vishnevetsky, A. n., Wahl, L. n., Wall, A. n., Wallace, F. n., Walsh, E. n., Wang, P. n., Ward, H. B., Warner, L. N., Weeks, L. D., Weiskopf, K. n., Wengrod, J. n., Williams, J. N., Winkler, M. n., Wong, J. L., Worster, D. n., Wright, A. n., Wunsch, C. n., Wynter, J. S., Yarbrough, C. n., Yau, W. Y., Yazdi, D. n., Yeh, J. n., Yialamas, M. A., Yozamp, N. n., Zambrotta, M. n., Zon, R. n. 2019; 12 (11): e006214

  Abstract

  Racial inequities for patients with heart failure (HF) have been widely documented. HF patients who receive cardiology care during a hospital admission have better outcomes. It is unknown whether there are differences in admission to a cardiology or general medicine service by race. This study examined the relationship between race and admission service, and its effect on 30-day readmission and mortality Methods: We performed a retrospective cohort study from September 2008 to November 2017 at a single large urban academic referral center of all patients self-referred to the emergency department and admitted to either the cardiology or general medicine service with a principal diagnosis of HF, who self-identified as white, black, or Latinx. We used multivariable generalized estimating equation models to assess the relationship between race and admission to the cardiology service. We used Cox regression to assess the association between race, admission service, and 30-day readmission and mortality.Among 1967 unique patients (66.7% white, 23.6% black, and 9.7% Latinx), black and Latinx patients had lower rates of admission to the cardiology service than white patients (adjusted rate ratio, 0.91; 95% CI, 0.84-0.98, for black; adjusted rate ratio, 0.83; 95% CI, 0.72-0.97 for Latinx). Female sex and age >75 years were also independently associated with lower rates of admission to the cardiology service. Admission to the cardiology service was independently associated with decreased readmission within 30 days, independent of race.Black and Latinx patients were less likely to be admitted to cardiology for HF care. This inequity may, in part, drive racial inequities in HF outcomes.

  View details for DOI 10.1161/CIRCHEARTFAILURE.119.006214

  View details for PubMedID 31658831

  View details for PubMedCentralID PMC7183732

• Doppler Assessment of Diastolic Function Reflect the Severity of Injury in Rats With Chronic Heart Failure. Journal of cardiac failure Sanchez, P., Lancaster, J. J., Weigand, K., Mohran, S. E., Goldman, S., Juneman, E. 2017; 23 (10): 753-761

  Abstract

  For chronic heart failure (CHF), more emphasis has been placed on evaluation of systolic as opposed to diastolic function. Within the study of diastology, measurements of left ventricular (LV) longitudinal myocardial relaxation have the most validation. Anterior wall radial myocardial tissue relaxation velocities along with mitral valve inflow (MVI) patterns are applicable diastolic parameters in the differentiation between moderate and severe disease in the ischemic rat model of CHF. Myocardial tissue relaxation velocities correlate with traditional measurements of diastolic function (ie, hemodynamics, Tau, and diastolic pressure-volume relationships).Male Sprague-Dawley rats underwent left coronary artery ligation or sham operation. Echocardiography was performed at 3 and 6 weeks after coronary ligation to evaluate LV ejection fraction (EF) and LV diastolic function through MVI patterns (E, A, and E/A) and Doppler imaging of the anterior wall (e' and a'). The rats were categorized into moderate or severe CHF according to their LV EF at 3 weeks postligation. Invasive hemodynamic measurements with solid-state pressure catheters were obtained at the 6-week endpoint. Moderate (N = 20) and severe CHF (N = 22) rats had significantly (P < .05) different EFs, hemodynamics, and diastolic pressure-volume relationships. Early diastolic anterior wall radial relaxation velocities as well as E/e' ratios separated moderate from severe CHF and both diastolic parameters had strong correlations with invasive hemodynamic measurements of diastolic function.Radial anterior wall e' and E/e' can be used for serial assessment of diastolic function in rats with moderate and severe CHF.

  View details for DOI 10.1016/j.cardfail.2017.08.446

  View details for PubMedID 28801075

• Effect of lysyl oxidase inhibition on angiotensin II-induced arterial hypertension, remodeling, and stiffness. PloS one Eberson, L. S., Sanchez, P. A., Majeed, B. A., Tawinwung, S., Secomb, T. W., Larson, D. F. 2015; 10 (4): e0124013

  Abstract

  It is well accepted that angiotensin II (Ang II) induces altered vascular stiffness through responses including both structural and material remodeling. Concurrent with remodeling is the induction of the enzyme lysyl oxidase (LOX) through which ECM proteins are cross-linked. The study objective was to determine the effect of LOX mediated cross-linking on vascular mechanical properties. Three-month old mice were chronically treated with Ang II with or without the LOX blocker, β -aminopropionitrile (BAPN), for 14 days. Pulse wave velocity (PWV) from Doppler measurements of the aortic flow wave was used to quantify in vivo vascular stiffness in terms of an effective Young's modulus. The increase in effective Young's modulus with Ang II administration was abolished with the addition of BAPN, suggesting that the material properties are a major controlling element in vascular stiffness. BAPN inhibited the Ang II induced collagen cross-link formation by 2-fold and PWV by 44% (P<0.05). Consistent with this observation, morphometric analysis showed that BAPN did not affect the Ang II mediated increase in medial thickness but significantly reduced the adventitial thickness. Since the hypertensive state contributes to the measured in vivo PWV stiffness, we removed the Ang II infusion pumps on Day 14 and achieved normal arterial blood pressures. With pump removal we observed a decrease of the PWV in the Ang II group to 25% above that of the control values (P=0.002), with a complete return to control values in the Ang II plus BAPN group. In conclusion, we have shown that the increase in vascular stiffness with 14 day Ang II administration results from a combination of hypertension-induced wall strain, adventitial wall thickening and Ang II mediated LOX ECM cross-linking, which is a major material source of vascular stiffening, and that the increased PWV was significantly inhibited with co-administration of BAPN.

  View details for DOI 10.1371/journal.pone.0124013

  View details for PubMedID 25875748

  View details for PubMedCentralID PMC4395147