1
|
Abbasi A, Li C, Dekle M, Bermudez CA, Brodie D, Sellke FW, Sodha NR, Ventetuolo CE, Eickhoff C. Interpretable machine learning-based predictive modeling of patient outcomes following cardiac surgery. J Thorac Cardiovasc Surg 2025; 169:114-123.e28. [PMID: 38040328 PMCID: PMC11133766 DOI: 10.1016/j.jtcvs.2023.11.034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Revised: 11/17/2023] [Accepted: 11/21/2023] [Indexed: 12/03/2023]
Abstract
BACKGROUND The clinical applicability of machine learning predictions of patient outcomes following cardiac surgery remains unclear. We applied machine learning to predict patient outcomes associated with high morbidity and mortality after cardiac surgery and identified the importance of variables to the derived model's performance. METHODS We applied machine learning to the Society of Thoracic Surgeons Adult Cardiac Surgery Database to predict postoperative hemorrhage requiring reoperation, venous thromboembolism (VTE), and stroke. We used permutation feature importance to identify variables important to model performance and a misclassification analysis to study the limitations of the model. RESULTS The study dataset included 662,772 subjects who underwent cardiac surgery between 2015 and 2017 and 240 variables. Hemorrhage requiring reoperation, VTE, and stroke occurred in 2.9%, 1.2%, and 2.0% of subjects, respectively. The model performed remarkably well at predicting all 3 complications (area under the receiver operating characteristic curve, 0.92-0.97). Preoperative and intraoperative variables were not important to model performance; instead, performance for the prediction of all 3 outcomes was driven primarily by several postoperative variables, including known risk factors for the complications, such as mechanical ventilation and new onset of postoperative arrhythmias. Many of the postoperative variables important to model performance also increased the risk of subject misclassification, indicating internal validity. CONCLUSIONS A machine learning model accurately and reliably predicts patient outcomes following cardiac surgery. Postoperative, as opposed to preoperative or intraoperative variables, are important to model performance. Interventions targeting this period, including minimizing the duration of mechanical ventilation and early treatment of new-onset postoperative arrhythmias, may help lower the risk of these complications.
Collapse
|
2
|
Kudelko K, Sung YK, Ventetuolo CE, Kawut S, Mazurek JA, McGlothlin D, Lahm T, Waxman A, Zamanian R. APOLLO Summary on Pulmonary Vascular Disease Fellowship Training. Chest 2024:S0012-3692(24)05716-7. [PMID: 39710248 DOI: 10.1016/j.chest.2024.11.044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2024] [Revised: 11/21/2024] [Accepted: 11/21/2024] [Indexed: 12/24/2024] Open
Abstract
Pulmonary vascular disease (PVD), and in particular, pulmonary hypertension (PH), is a highly specialized area of medicine comprised of complex diagnostics, classification systems, risk assessment tools, and therapeutics, the correct application of which has been shown to impact patient outcomes. The PVD scientific and patient community recognizes the importance of standardization of care patterns and has thus implemented a clinical accreditation process for PH care centers across the United States. However, a similar standardization system is lacking in PVD sub-specialty provider training. Non-Accreditation Council for Graduate Medical Education (ACGME) PVD advanced fellowships exist nationally, but do not provide a unified approach to trainee education. Therefore, first, a survey of all Pulmonary Hypertension Association (PHA)-accredited center directors across the U.S. was performed to gauge interest in a standardized educational initiative in the field of PVD. Second, a NAtional Consortium on PulmOnary VascuLar Disease FeLOwship Training (APOLLO) was founded to establish a common curriculum and set of training requirements across U.S. PVD programs. A particular emphasis was placed on the training requirements for provider competency in PH, because 1) reliable access to PH patients could be supported by all consortium institutions and 2) the consortium members felt that national PH training curriculums lacked standardization and detail. This article provides the results of the national survey, a guideline summary of the fellowship curriculum and training requirements, and a discussion of the impact of the consortium on PVD training and on the PVD subspecialty as a potential emerging formal discipline in internal medicine.
Collapse
|
3
|
Mehta A, Bansal M, Mehta C, Pillai AA, Allana S, Jentzer JC, Ventetuolo CE, Abbott JD, Vallabhajosyula S. Utilization of inpatient palliative care services in cardiac arrest complicating acute pulmonary embolism. Resusc Plus 2024; 20:100777. [PMID: 39314255 PMCID: PMC11417587 DOI: 10.1016/j.resplu.2024.100777] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/12/2024] [Revised: 09/02/2024] [Accepted: 09/06/2024] [Indexed: 09/25/2024] Open
Abstract
Introduction The role of palliative care services in patients with cardiac arrest complicating acute pulmonary embolism has been infrequently studied. Methods All adult admissions with pulmonary embolism complicating cardiac arrest were identified using the National Inpatient Sample (2016-2020). The primary outcome of interest was the utilization of palliative care services. Secondary outcomes included predictors of palliative care utilization and its association of with in-hospital mortality, do-not-resuscitate status, discharge disposition, length of stay, and total hospital charges. Multivariable regression analysis was used to adjust for confounding. Results Between 01/01/2016 and 12/31/2020, of the 7,320 admissions with pulmonary embolism complicating cardiac arrest, 1229 (16.8 %) received palliative care services. Admissions receiving palliative care were on average older (68.1 ± 0.9 vs. 63.2 ± 0.4 years) and with higher baseline comorbidity (Elixhauser index 6.3 ± 0.1 vs 5.6 ± 0.6) (all p < 0.001). Additionally, this cohort had higher rates of non-cardiac organ failure (respiratory, renal, hepatic, and neurological) and invasive mechanical ventilation (all p < 0.05). Catheter-directed therapy was used less frequently in the cohort receiving palliative care, (2.8 % vs 7.9 %; p < 0.001) whereas the rates of systemic thrombolysis, mechanical and surgical thrombectomy were comparable. The cohort receiving palliative care services had higher in-hospital mortality (85.7 % vs. 69.1 %; adjusted odds ratio 2.20 [95 % CI 1.41-3.42]; p < 0.001). This cohort also had higher rates of do-not-resuscitate status and fewer discharges to home, but comparable hospitalization costs and length of hospital stay. Conclusions Palliative care services are used in only 16.8 % of admissions with cardiac arrest complicating pulmonary embolism with significant differences in the populations, suggestive of selective consultation.
Collapse
|
4
|
Kawut SM, Feng R, Ellenberg SS, Zamanian R, Bull T, Chakinala M, Mathai SC, Hemnes A, Lin G, Doyle M, Andrew R, MacLean M, Stasinopoulos I, Austin E, DeMichele A, Shou H, Minhas J, Song N, Moutchia J, Ventetuolo CE. Pulmonary Hypertension and Anastrozole (PHANTOM): A Randomized, Double-Blind, Placebo-Controlled Trial. Am J Respir Crit Care Med 2024; 210:1143-1151. [PMID: 38747680 PMCID: PMC11544352 DOI: 10.1164/rccm.202402-0371oc] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2024] [Accepted: 05/15/2024] [Indexed: 11/02/2024] Open
Abstract
Rationale: Inhibition of aromatase with anastrozole reduces pulmonary hypertension in experimental models. Objectives: We aimed to determine whether anastrozole improved the 6-minute-walk distance (6MWD) at 6 months in pulmonary arterial hypertension (PAH). Methods: We performed a randomized, double-blind, placebo-controlled phase II clinical trial of anastrozole in subjects with PAH at seven centers. Eighty-four postmenopausal women with PAH and men with PAH were randomized in a 1:1 ratio to receive anastrozole 1 mg or placebo by mouth daily, stratified by sex using permuted blocks of variable sizes. All subjects and study staff were masked. The primary outcome was the change from baseline in 6MWD at 6 months. By intention-to-treat analysis, we estimated the treatment effect of anastrozole using linear regression models adjusted for sex and baseline 6MWD. Assuming 10% loss to follow-up, we anticipated having 80% power to detect a difference in the change in 6MWD of 22 meters. Measurements and Main Results: Forty-one subjects were randomized to placebo and 43 to anastrozole, and all received the allocated treatment. Three subjects in the placebo group and two in the anastrozole group discontinued the study drug. There was no significant difference in the change in 6MWD at 6 months (placebo-corrected treatment effect, -7.9 m; 95% confidence interval, -32.7 to 16.9; P = 0.53). There was no difference in adverse events between the groups. Conclusions: Anastrozole did not show a significant effect on 6MWD compared with placebo in postmenopausal women with PAH and in men with PAH. Anastrozole was safe and did not have adverse effects. Clinical trial registered with www.clincialtrials.gov (NCT03229499).
Collapse
|
5
|
Bashir Z, Ataklte F, Wang S, Chen EW, Kadiyala V, Sherrod CF, Has P, Song C, Ventetuolo CE, Simmons J, Haines P. Comparison of Left Ventricular Global Longitudinal Strain and Left Ventricular Ejection Fraction in Acute Respiratory Failure Patients Requiring Invasive Mechanical Ventilation. J Cardiovasc Dev Dis 2024; 11:339. [PMID: 39590182 PMCID: PMC11594607 DOI: 10.3390/jcdd11110339] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2024] [Revised: 10/17/2024] [Accepted: 10/21/2024] [Indexed: 11/28/2024] Open
Abstract
Left ventricular (LV) dysfunction is associated with poor clinical outcomes in acute respiratory failure (ARF). This study evaluates the efficacy of LV strain in detecting LV dysfunction in ARF patients requiring invasive mechanical ventilation (IMV) compared to conventionally measured left ventricular ejection fraction (LVEF). ARF patients requiring IMV who had echocardiography performed during MICU admission were included. LV global longitudinal strain (LVGLS) and LVEF were measured retrospectively using speckle tracking (STE) and traditional transthoracic echocardiography (TTE), respectively, by investigators blinded to the status of IMV and clinical data. The cohort was divided into three groups: TTE during IMV (TTE-IMV), before IMV (TTE-bIMV), and after IMV (TTE-aIMV). Multivariable regression models, adjusted for illness severity score, chronic cardiac disease, acute respiratory failure etiology, body mass index, chronic obstructive pulmonary disease, and obstructive sleep apnea, evaluated associations between LV function parameters and the presence of IMV. Among 376 patients, TTE-IMV, TTE-bIMV, and TTE-aIMV groups constituted 223, 68, and 85 patients, respectively. The median age was 65 years (IQR: 56-74), with 53.2% male participants. Adjusted models showed significantly higher LVGLS in groups not on IMV at the time of TTE (TTE-bIMV: β = 4.19, 95% CI 2.31 to 6.08, p < 0.001; TTE-aIMV: β = 3.79, 95% CI 2.03 to 5.55, p < 0.001), while no significant differences in LVEF were observed across groups. In a subgroup analysis of patients with LVEF ≥55%, the significant difference in LVGLS among the groups remained (TTE-bIMV: β = 4.18, 95% CI 2.22 to 6.15, p < 0.001; TTE-aIMV: β = 3.45, 95% CI 1.50 to 5.40, p < 0.001), but was no longer present in those with LVEF < 55%. This suggests an association between IMV and lower LVGLS in ARF patients requiring IMV, indicating that LVGLS may be a more sensitive marker for detecting subclinical LV dysfunction compared to LVEF in this population. Future studies should track and assess serial echocardiography data in the same cohort of patients pre-, during, and post-IMV in order to validate these findings and prognosticate STE-detected LV dysfunction in ARF patients requiring IMV.
Collapse
|
6
|
Leary PJ, Lindstrom M, Johnson CO, Emmons-Bell S, Rich S, Corris PA, DuBrock HM, Ventetuolo CE, Abate YH, Abdelmasseh M, Aboagye RG, Abualruz H, Abu-Gharbieh E, Aburuz S, Adamu LH, Adão R, Addo IY, Adedoyin RA, Adetunji JB, Adzigbli LA, Ahinkorah BO, Ahmad F, Ahmadzade AM, Ahmed A, Ahmed H, Ahmed SA, Akhlaghi S, Akkaif MA, Al Awaidy S, Alalalmeh SO, Albakri A, Aldawsari KA, Almahmeed W, Alshahrani NZ, Altaf A, Aly H, Alzoubi KH, Al-Zyoud WA, Amani R, Amusa GA, Andrei CL, Anwar S, Anyasodor AE, Aravkin AY, Areda D, Asmerom HA, Aujayeb A, Azzam AY, Babu AS, Bagherieh S, Baltatu OC, Barqawi HJ, Bastan MM, Batra K, Bayleyegn NS, Behnoush AH, Bhalla JS, Bhaskar S, Bhat V, Bitaraf S, Bitra VR, Boloor A, Braithwaite D, Brauer M, Bulto LN, Bustanji Y, Chattu VK, Chi G, Chichagi F, Chong B, Chowdhury R, Cindi Z, Cruz-Martins N, Dadana S, Dadras O, Dahiru T, Dai X, Dashtkoohi M, DeAngelo S, Debopadhaya S, Demessa BH, Desai HD, Dhulipala VR, Diaz MJ, Diress M, Do TC, Do THP, Doan KD, dos Santos WM, Doshi RP, Dowou RK, Dziedzic AM, Elhadi M, Etaee F, Fabin N, Fagbamigbe AF, Faris PS, Feyisa BR, Fortuna Rodrigues C, Gandhi AP, Ganiyani MA, Gela YY, Getie M, Ghaffari Jolfayi A, Ghasemzadeh A, Goldust M, Golechha M, Guan SY, Gudeta MD, Gupta M, Gupta R, Hadei M, Hammoud A, Hasnain MS, Hassan Zadeh Tabatabaei MS, Hay SI, Hegazi OE, Hemmati M, Hiraike Y, Hoan NQ, Hultström M, Huynh HH, Ibitoye SE, Ilesanmi OS, Ismail NE, Iwu CD, Jaggi K, Jain A, Jakovljevic M, Jee SH, Jeswani BM, Jha AK, Jokar M, Joseph N, Jozwiak JJ, Kabir H, Kahe F, Kamireddy A, Kanmanthareddy AR, Karimi H, Karimi Behnagh A, Kazemian S, Keshavarz P, Khalaji A, Khan MJ, Khidri FF, Kim MS, Kondlahalli SKMM, Kothari N, Krishan K, Kulimbet M, Kumar A, Latifinaibin K, Le TTT, Ledda C, Lee SW, Li MC, Lim SS, Liu S, Mahmoudi E, Makram OM, Malhotra K, Malik AA, Malta DC, Manla Y, Martorell M, Mehrabani-Zeinabad K, Merati M, Mestrovic T, Mirdamadi N, Misra AK, Mokdad AH, Moni MA, Moodi Ghalibaf A, Moraga P, Morovatdar N, Motappa R, Mousavi-Aghdas SA, Mustafa A, Naik GR, Najafi MS, Najdaghi S, Nanavaty DP, Narimani Davani D, Natto ZS, Nauman J, Nguyen DH, Nguyen PT, Niazi RK, Oancea B, Olanipekun TO, Oliveira GMM, Omar HA, P A MP, Pan F, Pandi-Perumal SR, Pantazopoulos I, Parikh RR, Petcu IR, Pham HN, Pham HT, Philip AK, Prates EJS, Puvvula J, Qian G, Rafferty Q, Rahim F, Rahimi M, Rahman M, Rahman MA, Rahmanian M, Rahmanian N, Rahmati M, Rahmati R, Ramadan MM, Ramphul K, Rana J, Rao IR, Rashedi S, Ravikumar N, Rawaf S, Ray A, Reddy MMRK, Redwan EMM, Rezaei N, Roy P, Saad AMA, Saddik BA, Sadeghi M, Saeb MR, Saheb Sharif-Askari F, Saheb Sharif-Askari N, Saleh MA, Sani NY, Saraswati U, Saravanan A, Saulam J, Schuermans A, Schumacher AE, Semagn BE, Sethi Y, Seylani A, Shafeghat M, Shahwan MJ, Shamim MA, Shamsi A, Sharfaei S, Sharma K, Sharma N, Sherif AA, Shiue I, Shorofi SA, Siddig EE, Singh H, Singh JA, Singh P, Singh S, Sobia F, Solanki R, Solanki S, Spartalis M, Swain CK, Szarpak L, Tabatabaei SM, Tabche C, Tamuzi JL, Tan KK, Teramoto M, Tharwat S, Thienemann F, Truyen TTTT, Tsegay GM, Udoakang AJ, Van den Eynde J, Varthya SB, Verma M, Vervoort D, Vinayak M, Viskadourou M, Wang F, Wickramasinghe ND, Wilandika A, Xu S, Yu C, Zare I, Zeineddine MA, Zhang ZJ, Zhu L, Zhumagaliuly A, Zielińska M, Zyoud SH, Murray CJL, Roth GA. Global, regional, and national burden of pulmonary arterial hypertension, 1990-2021: a systematic analysis for the Global Burden of Disease Study 2021. THE LANCET. RESPIRATORY MEDICINE 2024:S2213-2600(24)00295-9. [PMID: 39433052 DOI: 10.1016/s2213-2600(24)00295-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/17/2024] [Revised: 08/16/2024] [Accepted: 08/22/2024] [Indexed: 10/23/2024]
Abstract
BACKGROUND Pulmonary arterial hypertension (PAH) is a vascular disease characterised by restricted flow and high pressure through the pulmonary arteries, leading to progressive right heart failure and death. This study reports the global burden of PAH, leveraging all available data and using methodology of the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) to understand the epidemiology of this under-researched and morbid disease. METHODS Prior to the current effort, the burden of PAH was included in GBD as a non-specific contributor to "other cardiovascular and circulatory disease" burden. In this study, PAH was distinguished as its own cause of death and disability in GBD, producing comparable and consistent estimates of PAH burden. We used epidemiological and vital registry data to estimate the non-fatal and fatal burden of PAH in 204 countries and territories from 1990 to 2021 using standard GBD modelling approaches. We specifically focused on PAH (group 1 pulmonary hypertension), and did not include pulmonary hypertension groups 2-5. FINDINGS In 2021, there were an estimated 192 000 (95% uncertainty interval [UI] 155 000-236 000) prevalent cases of PAH globally. Of these, 119 000 (95 900-146 000) were in females (62%) and 73 100 (58 900-89 600) in males (38%). The age-standardised prevalence was 2·28 cases per 100 000 population (95% UI 1·85-2·80). Prevalence increased with age such that the highest prevalence was among individuals aged 75-79 years. In 2021, there were 22 000 deaths (18 200-25 400) attributed to PAH globally, with an age-standardised mortality rate of 0·27 deaths from PAH per 100 000 population (0·23-0·32). The burden of disease appears to be improving over time (38·2% improvement in age-standardised years of life lost [YLLs] in 2021 relative to 1990). YLLs attributed to PAH were similar to estimates for conditions such as chronic myeloid leukaemia, multiple sclerosis, and Crohn's disease. INTERPRETATION PAH is a rare but fatal disease that accounts for a considerable health-associated burden worldwide. PAH is disproportionally diagnosed among females and older adults. FUNDING Cardiovascular Medical Research and Education Fund and the Bill & Melinda Gates Foundation.
Collapse
|
7
|
Scott JV, Moutchia J, McClelland RL, Al-Naamani N, Weinberg E, Palevsky HI, Minhas J, Appleby DK, Smith A, Pugliese SC, Ventetuolo CE, Kawut SM. Novel Liver Injury Phenotypes and Outcomes in Clinical Trial Participants with Pulmonary Hypertension. Am J Respir Crit Care Med 2024; 210:1045-1056. [PMID: 38820270 PMCID: PMC11531102 DOI: 10.1164/rccm.202311-2196oc] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Accepted: 05/29/2024] [Indexed: 06/02/2024] Open
Abstract
Rationale: Pulmonary arterial hypertension (PAH) and chronic thromboembolic pulmonary hypertension (CTEPH) cause right ventricular dysfunction, which can impact other solid organs. However, the profiles and consequences of hepatic injury resulting from PAH and CTEPH have not been well studied. Objectives: We aimed to identify underlying patterns of liver injury in a cohort of patients with PAH and CTEPH enrolled in 15 randomized clinical trials conducted between 1998 and 2014. Methods: We used unsupervised machine learning to identify liver injury clusters in 13 trials and validated the findings in two additional trials. We then determined whether these liver injury clusters were associated with clinical outcomes or treatment effect heterogeneity. Measurements and Main Results: Our training dataset included 4,219 patients and our validation dataset included 1,756 patients with serum total bilirubin, alkaline phosphatase, aspartate aminotransferase, alanine aminotransferase, and albumin data. Using k-means clustering, we identified phenotypes with no liver injury, hepatocellular injury, cholestatic injury, and combined injury patterns. Patients in the cholestatic injury liver cluster had the shortest time to clinical worsening and the highest risk of mortality. The cholestatic injury group also experienced the greatest placebo-corrected treatment effect on 6-minute-walk distance. Randomization to the experimental arm transitioned patients to a healthier liver status. Conclusions: Liver injury was associated with adverse outcomes in patients with PAH and CTEPH. Randomization to active treatment had beneficial effects on liver health compared with placebo. The role of liver disease (often subclinical) in determining outcomes warrants prospective studies.
Collapse
|
8
|
Kalra A, Bachina P, Shou BL, Hwang J, Barshay M, Kulkarni S, Sears I, Eickhoff C, Bermudez CA, Brodie D, Ventetuolo CE, Whitman GJ, Abbasi A, Cho SM. Using machine learning to predict neurologic injury in venovenous extracorporeal membrane oxygenation recipients: An ELSO Registry analysis. JTCVS OPEN 2024; 21:140-167. [PMID: 39534333 PMCID: PMC11551311 DOI: 10.1016/j.xjon.2024.06.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/02/2024] [Revised: 05/10/2024] [Accepted: 06/10/2024] [Indexed: 11/16/2024]
Abstract
Background Venovenous extracorporeal membrane oxygenation (VV-ECMO) is associated with acute brain injury (ABI), including central nervous system (CNS) ischemia (defined as ischemic stroke or hypoxic-ischemic brain injury [HIBI]) and intracranial hemorrhage (ICH). Data on prediction models for neurologic outcomes in VV-ECMO are limited. Methods We analyzed adult (age ≥18 years) VV-ECMO patients in the Extracorporeal Life Support Organization (ELSO) Registry (2009-2021) from 676 centers. ABI was defined as CNS ischemia, ICH, brain death, and seizures. Data on 67 variables were extracted, including clinical characteristics and pre-ECMO/on-ECMO variables. Random forest, CatBoost, LightGBM, and XGBoost machine learning (ML) algorithms (10-fold leave-one-out cross-validation) were used to predict ABI. Feature importance scores were used to pinpoint the most important variables for predicting ABI. Results Of 37,473 VV-ECMO patients (median age, 48.1 years; 63% male), 2644 (7.1%) experienced ABI, including 610 (2%) with CNS ischemia and 1591 (4%) with ICH. The areas under the receiver operating characteristic curve for predicting ABI, CNS ischemia, and ICH were 0.70, 0.68, and 0.70, respectively. The accuracy, positive predictive value, and negative predictive value for ABI were 85%, 19%, and 95%, respectively. ML identified higher center volume, pre-ECMO cardiac arrest, higher ECMO pump flow, and elevated on-ECMO serum lactate level as the most important risk factors for ABI and its subtypes. Conclusions This is the largest study of VV-ECMO patients to use ML to predict ABI reported to date. Performance was suboptimal, likely due to lack of standardization of neuromonitoring/imaging protocols and data granularity in the ELSO Registry. Standardized neurologic monitoring and imaging are needed across ELSO centers to detect the true prevalence of ABI.
Collapse
|
9
|
Hough RF, Alvira CM, Bastarache JA, Erzurum SC, Kuebler WM, Schmidt EP, Shimoda LA, Abman SH, Alvarez DF, Belvitch P, Bhattacharya J, Birukov KG, Chan SY, Cornfield DN, Dudek SM, Garcia JGN, Harrington EO, Hsia CCW, Islam MN, Jonigk DD, Kalinichenko VV, Kolb TM, Lee JY, Mammoto A, Mehta D, Rounds S, Schupp JC, Shaver CM, Suresh K, Tambe DT, Ventetuolo CE, Yoder MC, Stevens T, Damarla M. Studying the Pulmonary Endothelium in Health and Disease: An Official American Thoracic Society Workshop Report. Am J Respir Cell Mol Biol 2024; 71:388-406. [PMID: 39189891 PMCID: PMC11450313 DOI: 10.1165/rcmb.2024-0330st] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2024] [Indexed: 08/28/2024] Open
Abstract
Lung endothelium resides at the interface between the circulation and the underlying tissue, where it senses biochemical and mechanical properties of both the blood as it flows through the vascular circuit and the vessel wall. The endothelium performs the bidirectional signaling between the blood and tissue compartments that is necessary to maintain homeostasis while physically separating both, facilitating a tightly regulated exchange of water, solutes, cells, and signals. Disruption in endothelial function contributes to vascular disease, which can manifest in discrete vascular locations along the artery-to-capillary-to-vein axis. Although our understanding of mechanisms that contribute to endothelial cell injury and repair in acute and chronic vascular disease have advanced, pathophysiological mechanisms that underlie site-specific vascular disease remain incompletely understood. In an effort to improve the translatability of mechanistic studies of the endothelium, the American Thoracic Society convened a workshop to optimize rigor, reproducibility, and translation of discovery to advance our understanding of endothelial cell function in health and disease.
Collapse
|
10
|
Bansal M, Mehta A, Balakrishna AM, Saad M, Ventetuolo CE, Roswell RO, Poppas A, Abbott JD, Vallabhajosyula S. Race, Ethnicity, and Gender Disparities in Acute Myocardial Infarction. Crit Care Clin 2024; 40:685-707. [PMID: 39218481 DOI: 10.1016/j.ccc.2024.05.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/04/2024]
Abstract
Cardiovascular disease continues to be the leading cause of morbidity and mortality in the United States. Despite advancements in medical care, there remain persistent racial, ethnic, and gender disparity in the diagnosis, treatment, and prognosis of individuals with cardiovascular disease. In this review we seek to discuss differences in pathophysiology, clinical course, and risk profiles in the management and outcomes of acute myocardial infarction and related high-risk states. We also seek to highlight the demographic and psychosocial inequities that cause disparities in acute cardiovascular care.
Collapse
|
11
|
Vallabhajosyula S, Ogunsakin A, Jentzer JC, Sinha SS, Kochar A, Gerberi DJ, Mullin CJ, Ahn SH, Sodha NR, Ventetuolo CE, Levine DJ, Abbott BG, Aliotta JM, Poppas A, Abbott JD. Multidisciplinary Care Teams in Acute Cardiovascular Care: A Review of Composition, Logistics, Outcomes, Training, and Future Directions. J Card Fail 2024; 30:1367-1383. [PMID: 39389747 DOI: 10.1016/j.cardfail.2024.06.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2024] [Revised: 05/27/2024] [Accepted: 06/21/2024] [Indexed: 10/12/2024]
Abstract
As cardiovascular care continues to advance and with an aging population with higher comorbidities, the epidemiology of the cardiac intensive care unit has undergone a paradigm shift. There has been increasing emphasis on the development of multidisciplinary teams (MDTs) for providing holistic care to complex critically ill patients, analogous to heart teams for chronic cardiovascular care. Outside of cardiovascular medicine, MDTs in critical care medicine focus on implementation of guideline-directed care, prevention of iatrogenic harm, communication with patients and families, point-of-care decision-making, and the development of care plans. MDTs in acute cardiovascular care include physicians from cardiovascular medicine, critical care medicine, interventional cardiology, cardiac surgery, and advanced heart failure, in addition to nonphysician team members. In this document, we seek to describe the changes in patients in the cardiac intensive care unit, health care delivery, composition, logistics, outcomes, training, and future directions for MDTs involved in acute cardiovascular care. As a part of the comprehensive review, we performed a scoping of concepts of MDTs, acute hospital care, and cardiovascular conditions and procedures.
Collapse
|
12
|
Wang S, Bashir Z, Chen EW, Kadiyala V, Sherrod CF, Has P, Song C, Ventetuolo CE, Simmons J, Haines P. Invasive Mechanical Ventilation Is Associated with Worse Right Ventricular Strain in Acute Respiratory Failure Patients. J Cardiovasc Dev Dis 2024; 11:246. [PMID: 39195154 DOI: 10.3390/jcdd11080246] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2024] [Revised: 08/07/2024] [Accepted: 08/07/2024] [Indexed: 08/29/2024] Open
Abstract
Right ventricular (RV) dysfunction is associated with poor prognosis in acute respiratory failure (ARF). Our study evaluates the efficacy of RV strain in detecting RV dysfunction in ARF patients requiring invasive mechanical ventilation (IMV) compared to tricuspid annular plane systolic excursion (TAPSE). In this retrospective study involving 376 patients diagnosed with ARF and requiring IMV, we extracted clinical and outcome data from patient records. RV global longitudinal strain (RVGLS), free wall longitudinal strain (FWLS), and TAPSE were measured retrospectively using speckle tracking echocardiography (STE) and traditional echocardiography, respectively. We divided the cohort into three groups: TTE during IMV (TTE-IMV, 223 patients), before IMV (TTE-bIMV, 68 patients), and after IMV (TTE-aIMV, 85 patients). Multivariable regression analysis, adjusted for covariates, revealed significantly higher RVGLS and FWLS in the groups not on IMV at the time of TTE compared to the TTE-IMV group. Specifically, the TTE-bIMV group showed higher RVGLS (β = 7.28, 95% CI 5.07, 9.48) and FWLS (β = 5.83, 95% CI 3.36, 8.31), while the TTE-aIMV group exhibited higher RVGLS (β = 9.39, 95% CI 6.10, 12.69) and FWLS (β = 7.54, 95% CI 4.83, 10.24). TAPSE did not reveal any significant differences across the groups. Our study suggests an association between IMV and lower RVGLS and FWLS in ARF patients, indicating that IMV itself may contribute to RV dysfunction. RVGLS and FWLS appear to be more sensitive than TAPSE in detecting changes in RV function that were previously subclinical in patients on IMV. Prospective studies with TTE before, during, and after IMV are necessary to assess the primary driver of RV dysfunction and to prognosticate STE-detected RV dysfunction in this population.
Collapse
|
13
|
Kalra A, Bachina P, Shou BL, Hwang J, Barshay M, Kulkarni S, Sears I, Eickhoff C, Bermudez CA, Brodie D, Ventetuolo CE, Kim BS, Whitman GJ, Abbasi A, Cho SM. Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: An Extracorporeal Life Support Organization Registry analysis. JTCVS OPEN 2024; 20:64-88. [PMID: 39296456 PMCID: PMC11405982 DOI: 10.1016/j.xjon.2024.06.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/10/2024] [Revised: 05/23/2024] [Accepted: 06/03/2024] [Indexed: 09/21/2024]
Abstract
Objective We aimed to determine if machine learning can predict acute brain injury and to identify modifiable risk factors for acute brain injury in patients receiving venoarterial extracorporeal membrane oxygenation. Methods We included adults (age ≥18 years) receiving venoarterial extracorporeal membrane oxygenation or extracorporeal cardiopulmonary resuscitation in the Extracorporeal Life Support Organization Registry (2009-2021). Our primary outcome was acute brain injury: central nervous system ischemia, intracranial hemorrhage, brain death, and seizures. We used Random Forest, CatBoost, LightGBM, and XGBoost machine learning algorithms (10-fold leave-1-out cross-validation) to predict and identify features most important for acute brain injury. We extracted 65 total features: demographics, pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation laboratory values, and pre-extracorporeal membrane oxygenation/on-extracorporeal membrane oxygenation settings. Results Of 35,855 patients receiving venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation) (median age of 57.8 years, 66% were male), 7.7% (n = 2769) experienced acute brain injury. In venoarterial extracorporeal membrane oxygenation (nonextracorporeal cardiopulmonary resuscitation), the area under the receiver operator characteristic curves to predict acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.67, 0.67, and 0.62, respectively. The true-positive, true-negative, false-positive, false-negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively, for acute brain injury. Longer extracorporeal membrane oxygenation duration, higher 24-hour extracorporeal membrane oxygenation pump flow, and higher on-extracorporeal membrane oxygenation partial pressure of oxygen were associated with acute brain injury. Of 10,775 patients receiving extracorporeal cardiopulmonary resuscitation (median age of 57.1 years, 68% were male), 16.5% (n = 1787) experienced acute brain injury. The area under the receiver operator characteristic curves for acute brain injury, central nervous system ischemia, and intracranial hemorrhage were 0.72, 0.73, and 0.69, respectively. Longer extracorporeal membrane oxygenation duration, older age, and higher 24-hour extracorporeal membrane oxygenation pump flow were associated with acute brain injury. Conclusions In the largest study predicting neurological complications with machine learning in extracorporeal membrane oxygenation, longer extracorporeal membrane oxygenation duration and higher 24-hour pump flow were associated with acute brain injury in nonextracorporeal cardiopulmonary resuscitation and extracorporeal cardiopulmonary resuscitation venoarterial extracorporeal membrane oxygenation.
Collapse
|
14
|
Moutchia J, McClelland RL, Al-Naamani N, Appleby DH, Holmes JH, Minhas J, Mazurek JA, Palevsky HI, Ventetuolo CE, Kawut SM. Pulmonary arterial hypertension treatment: an individual participant data network meta-analysis. Eur Heart J 2024; 45:1937-1952. [PMID: 38416633 PMCID: PMC11143388 DOI: 10.1093/eurheartj/ehae049] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Revised: 11/20/2023] [Accepted: 01/18/2024] [Indexed: 03/01/2024] Open
Abstract
BACKGROUND AND AIMS Effective therapies that target three main signalling pathways are approved to treat pulmonary arterial hypertension (PAH). However, there are few large patient-level studies that compare the effectiveness of these pathways. The aim of this analysis was to compare the effectiveness of the treatment pathways in PAH and to assess treatment heterogeneity. METHODS A network meta-analysis was performed using individual participant data of 6811 PAH patients from 20 Phase III randomized clinical trials of therapy for PAH that were submitted to the US Food and Drug Administration. Individual drugs were grouped by the following treatment pathways: endothelin, nitric oxide, and prostacyclin pathways. RESULTS The mean (±standard deviation) age of the sample was 49.2 (±15.4) years; 78.4% were female, 59.7% had idiopathic PAH, and 36.5% were on background PAH therapy. After covariate adjustment, targeting the endothelin + nitric oxide pathway {β: 43.7 m [95% confidence interval (CI): 32.9, 54.4]}, nitric oxide pathway [β: 29.4 m (95% CI: 22.6, 36.3)], endothelin pathway [β: 25.3 m (95% CI: 19.8, 30.8)], and prostacyclin pathway [oral/inhaled β: 19.1 m (95% CI: 14.2, 24.0), intravenous/subcutaneous β: 24.4 m (95% CI: 15.1, 33.7)] significantly increased 6 min walk distance at 12 or 16 weeks compared with placebo. Treatments also significantly reduced the likelihood of having clinical worsening events. There was significant heterogeneity of treatment effects by age, body mass index, hypertension, diabetes, and coronary artery disease. CONCLUSIONS Drugs targeting the three traditional treatment pathways significantly improve outcomes in PAH, with significant treatment heterogeneity in patients with some comorbidities. Randomized clinical trials are warranted to identify the most effective treatment strategies in a personalized approach.
Collapse
|
15
|
DesJardin JT, Kime N, Kolaitis NA, Kronmal RA, Lammi MR, Mathai SC, Ventetuolo CE, De Marco T. Investigating the "sex paradox" in pulmonary arterial hypertension: Results from the Pulmonary Hypertension Association Registry (PHAR). J Heart Lung Transplant 2024; 43:901-910. [PMID: 38360160 PMCID: PMC11500812 DOI: 10.1016/j.healun.2024.02.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2023] [Revised: 01/24/2024] [Accepted: 02/07/2024] [Indexed: 02/17/2024] Open
Abstract
BACKGROUND Female sex is a significant risk factor for pulmonary arterial hypertension (PAH), yet males with PAH have worse survival - a phenomenon referred to as the "sex paradox" in PAH. METHODS All adult PAH patients in the Pulmonary Hypertension Association Registry (PHAR) with congruent sex and gender were included. Baseline differences in demographics, hemodynamics, functional parameters, and quality of life were assessed by sex. Kaplan-Meier survival analysis was used to evaluate survival by sex. Mediation analysis was conducted with Cox proportional hazards regression by comparing the unadjusted hazard ratios for sex before and after adjustment for covariates. The plausibility of collider-stratification bias was assessed by modeling how large an unmeasured factor would have to be to generate the observed sex-based mortality differences. Subgroup analysis was performed on idiopathic and incident patients. RESULTS Among the 1,891 patients included, 75% were female. Compared to men, women had less favorable hemodynamics, lower 6-minute walk distance, more PAH therapies, and worse functional class; however, sex-based differences were less pronounced when accounting for body surface area or expected variability by gender. On multivariate analysis, women had a 48% lower risk of death compared to men (Hazard Ratio 0.52, 95% Confidence interval 0.36 - 0.74, p < 0.001). Modeling found that under reasonable assumptions collider-stratification could account for sex-based differences in mortality. CONCLUSIONS In this large registry of PAH patients new to a care center, men had worse survival than women despite having more favorable baseline characteristics. Collider-stratification bias could account for the observed greater mortality among men.
Collapse
|
16
|
Singh N, Al-Naamani N, Brown MB, Long GM, Thenappan T, Umar S, Ventetuolo CE, Lahm T. Extrapulmonary manifestations of pulmonary arterial hypertension. Expert Rev Respir Med 2024; 18:189-205. [PMID: 38801029 DOI: 10.1080/17476348.2024.2361037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Accepted: 05/24/2024] [Indexed: 05/29/2024]
Abstract
INTRODUCTION Extrapulmonary manifestations of pulmonary arterial hypertension (PAH) may play a critical pathobiological role and a deeper understanding will advance insight into mechanisms and novel therapeutic targets. This manuscript reviews our understanding of extrapulmonary manifestations of PAH. AREAS COVERED A group of experts was assembled and a complimentary PubMed search performed (October 2023 - March 2024). Inflammation is observed throughout the central nervous system and attempts at manipulation are an encouraging step toward novel therapeutics. Retinal vascular imaging holds promise as a noninvasive method of detecting early disease and monitoring treatment responses. PAH patients have gut flora alterations and dysbiosis likely plays a role in systemic inflammation. Despite inconsistent observations, the roles of obesity, insulin resistance and dysregulated metabolism may be illuminated by deep phenotyping of body composition. Skeletal muscle dysfunction is perpetuated by metabolic dysfunction, inflammation, and hypoperfusion, but exercise training shows benefit. Renal, hepatic, and bone marrow abnormalities are observed in PAH and may represent both end-organ damage and disease modifiers. EXPERT OPINION Insights into systemic manifestations of PAH will illuminate disease mechanisms and novel therapeutic targets. Additional study is needed to understand whether extrapulmonary manifestations are a cause or effect of PAH and how manipulation may affect outcomes.
Collapse
|
17
|
Kalra A, Bachina P, Shou BL, Hwang J, Barshay M, Kulkarni S, Sears I, Eickhoff C, Bermudez CA, Brodie D, Ventetuolo CE, Kim BS, Whitman GJR, Abbasi A, Cho SM. Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry. RESEARCH SQUARE 2024:rs.3.rs-3848514. [PMID: 38260374 PMCID: PMC10802703 DOI: 10.21203/rs.3.rs-3848514/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/24/2024]
Abstract
Objective To determine if machine learning (ML) can predict acute brain injury (ABI) and identify modifiable risk factors for ABI in venoarterial extracorporeal membrane oxygenation (VA-ECMO) patients. Design Retrospective cohort study of the Extracorporeal Life Support Organization (ELSO) Registry (2009-2021). Setting International, multicenter registry study of 676 ECMO centers. Patients Adults (≥18 years) supported with VA-ECMO or extracorporeal cardiopulmonary resuscitation (ECPR). Interventions None. Measurements and Main Results Our primary outcome was ABI: central nervous system (CNS) ischemia, intracranial hemorrhage (ICH), brain death, and seizures. We utilized Random Forest, CatBoost, LightGBM and XGBoost ML algorithms (10-fold leave-one-out cross-validation) to predict and identify features most important for ABI. We extracted 65 total features: demographics, pre-ECMO/on-ECMO laboratory values, and pre-ECMO/on-ECMO settings.Of 35,855 VA-ECMO (non-ECPR) patients (median age=57.8 years, 66% male), 7.7% (n=2,769) experienced ABI. In VA-ECMO (non-ECPR), the area under the receiver-operator characteristics curves (AUC-ROC) to predict ABI, CNS ischemia, and ICH was 0.67, 0.67, and 0.62, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively for ABI. Longer ECMO duration, higher 24h ECMO pump flow, and higher on-ECMO PaO2 were associated with ABI.Of 10,775 ECPR patients (median age=57.1 years, 68% male), 16.5% (n=1,787) experienced ABI. The AUC-ROC for ABI, CNS ischemia, and ICH was 0.72, 0.73, and 0.69, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 61%, 70%, 30%, 39%, 29% and 90%, respectively, for ABI. Longer ECMO duration, younger age, and higher 24h ECMO pump flow were associated with ABI. Conclusions This is the largest study predicting neurological complications on sufficiently powered international ECMO cohorts. Longer ECMO duration and higher 24h pump flow were associated with ABI in both non-ECPR and ECPR VA-ECMO.
Collapse
|
18
|
Kalra A, Bachina P, Shou BL, Hwang J, Barshay M, Kulkarni S, Sears I, Eickhoff C, Bermudez CA, Brodie D, Ventetuolo CE, Whitman GJR, Abbasi A, Cho SM. Utilizing Machine Learning to Predict Neurological Injury in Venovenous Extracorporeal Membrane Oxygenation Patients: An Extracorporeal Life Support Organization Registry Analysis. RESEARCH SQUARE 2023:rs.3.rs-3779429. [PMID: 38196631 PMCID: PMC10775358 DOI: 10.21203/rs.3.rs-3779429/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/11/2024]
Abstract
Background Venovenous extracorporeal membrane oxygenation (VV-ECMO) is associated with acute brain injury (ABI), including central nervous system (CNS) ischemia (defined as ischemic stroke or hypoxic-ischemic brain injury) and intracranial hemorrhage (ICH). There is limited data on prediction models for ABI and neurological outcomes in VV-ECMO. Research Question Can machine learning (ML) accurately predict ABI and identify modifiable factors of ABI in VV-ECMO? Study Design and Methods We analyzed adult (≥18 years) VV-ECMO patients in the Extracorporeal Life Support Organization Registry (2009-2021) from 676 centers. ABI was defined as CNS ischemia, ICH, brain death, and seizures. Overall, 65 total variables were extracted including clinical characteristics and pre-ECMO and on-ECMO variables. Random Forest, CatBoost, LightGBM, and XGBoost ML algorithms (10-fold leave-one-out cross-validation) were used to predict ABI. Feature Importance Scores were used to pinpoint variables most important for predicting ABI. Results Of 37,473 VV-ECMO patients (median age=48.1 years, 63% male), 2,644 (7.1%) experienced ABI: 610 (2%) and 1,591 (4%) experienced CNS ischemia and ICH, respectively. The median ECMO duration was 10 days (interquartile range=5-20 days). The area under the receiver-operating characteristics curves to predict ABI, CNS ischemia, and ICH were 0.67, 0.63, and 0.70, respectively. The accuracy, positive predictive, and negative predictive values for ABI were 79%, 15%, and 95%, respectively. ML identified pre-ECMO cardiac arrest as the most important risk factor for ABI while ECMO duration and bridge to transplantation as an indication for ECMO were associated with lower risk of ABI. Interpretation This is the first study to use machine learning to predict ABI in a large cohort of VV-ECMO patients. Performance was sub-optimal due to the low reported prevalence of ABI with lack of standardization of neuromonitoring/imaging protocols and data granularity in the ELSO Registry. Standardized neurological monitoring and imaging protocols may improve machine learning performance to predict ABI.
Collapse
|
19
|
Singh N, Eickhoff C, Garcia-Agundez A, Bertone P, Paudel SS, Tambe DT, Litzky LA, Cox-Flaherty K, Klinger JR, Monaghan SF, Mullin CJ, Pereira M, Walsh T, Whittenhall M, Stevens T, Harrington EO, Ventetuolo CE. Transcriptional profiles of pulmonary artery endothelial cells in pulmonary hypertension. Sci Rep 2023; 13:22534. [PMID: 38110438 PMCID: PMC10728171 DOI: 10.1038/s41598-023-48077-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2023] [Accepted: 11/22/2023] [Indexed: 12/20/2023] Open
Abstract
Pulmonary arterial hypertension (PAH) is characterized by endothelial cell (EC) dysfunction. There are no data from living patients to inform whether differential gene expression of pulmonary artery ECs (PAECs) can discern disease subtypes, progression and pathogenesis. We aimed to further validate our previously described method to propagate ECs from right heart catheter (RHC) balloon tips and to perform additional PAEC phenotyping. We performed bulk RNA sequencing of PAECs from RHC balloons. Using unsupervised dimensionality reduction and clustering we compared transcriptional signatures from PAH to controls and other forms of pulmonary hypertension. Select PAEC samples underwent single cell and population growth characterization and anoikis quantification. Fifty-four specimens were analyzed from 49 subjects. The transcriptome appeared stable over limited passages. Six genes involved in sex steroid signaling, metabolism, and oncogenesis were significantly upregulated in PAH subjects as compared to controls. Genes regulating BMP and Wnt signaling, oxidative stress and cellular metabolism were differentially expressed in PAH subjects. Changes in gene expression tracked with clinical events in PAH subjects with serial samples over time. Functional assays demonstrated enhanced replication competency and anoikis resistance. Our findings recapitulate fundamental biological processes of PAH and provide new evidence of a cancer-like phenotype in ECs from the central vasculature of PAH patients. This "cell biopsy" method may provide insight into patient and lung EC heterogeneity to advance precision medicine approaches in PAH.
Collapse
|
20
|
Johnson SW, Ventetuolo CE. Reply to Olschewski et al.. Am J Respir Crit Care Med 2023; 208:1340-1341. [PMID: 37871322 PMCID: PMC10765401 DOI: 10.1164/rccm.202310-1770le] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Accepted: 10/20/2023] [Indexed: 10/25/2023] Open
|
21
|
Weatherald J, Moutchia J, Al-Naamani N, McClelland RL, Ventetuolo CE, Palevsky HI, Harhay MO, Kawut SM. Win Statistics in Pulmonary Arterial Hypertension Clinical Trials. Am J Respir Crit Care Med 2023; 208:1231-1234. [PMID: 37734029 PMCID: PMC10868347 DOI: 10.1164/rccm.202305-0800le] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Accepted: 09/21/2023] [Indexed: 09/23/2023] Open
|
22
|
Fling C, De Marco T, Kime NA, Lammi MR, Oppegard LJ, Ryan JJ, Ventetuolo CE, White RJ, Zamanian RT, Leary PJ. Regional Variation in Pulmonary Arterial Hypertension in the United States: The Pulmonary Hypertension Association Registry. Ann Am Thorac Soc 2023; 20:1718-1725. [PMID: 37683277 PMCID: PMC10704225 DOI: 10.1513/annalsats.202305-424oc] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/08/2023] [Accepted: 09/07/2023] [Indexed: 09/10/2023] Open
Abstract
Rationale: Pulmonary arterial hypertension (PAH) is a heterogeneous disease within a complex diagnostic and treatment environment. Other complex heart and lung diseases have substantial regional variation in characteristics and outcomes; however, this has not been previously described in PAH. Objectives: To identify baseline differences between U.S. census regions in the characteristics and outcomes for participants in the Pulmonary Hypertension Association Registry (PHAR). Methods: Adults with PAH were divided into regional groups (Northeast, South, Midwest, and West), and baseline differences between census regions were presented. Kaplan-Meier survival analyses and Cox proportional hazards were used to estimate the association between region and mortality in unadjusted and adjusted models. Results: Substantial differences by census regions were seen in age, race, ethnicity, marital status, employment, insurance payor breakdown, active smoking, and current alcohol use. Differences were also seen in PAH etiology and baseline 6-minute walk distance test results. Treatment characteristics varied by census region, and mortality appeared to be lower in PHAR participants in the West (hazard ratio, 0.60; 95% confidence interval, 0.43-0.83, P = 0.005). This difference was not readily explained by differences in demographic characteristics, PAH etiology, baseline severity, baseline medication regimen, or disease prevalence. Conclusions: The present study suggests significant regional variation among participants at accredited pulmonary vascular disease centers in multiple baseline characteristics and mortality. This variation may have implications for clinical research planning and represent an important focus for further study to better understand whether there are remediable care aspects that can be addressed in the pursuit of providing equitable care in the United States.
Collapse
|
23
|
Sears I, Garcia-Agundez A, Zerveas G, Rudman W, Mercurio L, Ventetuolo CE, Abbasi A, Eickhoff C. Leveraging Unlabeled Electroencephalographic Data to Predict Neurological Recovery for Comatose Patients Following Cardiac Arrest. COMPUTING IN CARDIOLOGY 2023; 50:10.22489/CinC.2023.308. [PMID: 39526226 PMCID: PMC11544604 DOI: 10.22489/cinc.2023.308] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2024]
Abstract
In response to the 2023 George B. Moody PhysioNet Challenge, we propose an automated, unsupervised pre-training approach to boost the performance of models that predict neurologic outcomes after cardiac arrest. Our team, (BrownBAI), developed a model architecture consisting of three parts: a pre-processor to convert raw electroencephalograms (EEGs) into two-dimensional spectrograms, a three-layer convolutional neural network (CNN) encoder for unsupervised pre-training, and a time series transformer (TST) model. We trained the CNN encoder on unlabeled five-minute EEG samples from the Temple University EEG Corpus (TUEG), which included more than 20x the patients available in the PhysioNet competition training dataset. We then incorporated the pre-trained encoder into the TST as a base layer and trained the composite model as a classifier on EEGs from the 2023 PhysioNet Challenge dataset. Our team was not able to submit an official competition entry and was therefore not scored on the test set. However, in a side-by-side comparison on the competition training dataset, our model performed better with a pretrained (competition score 0.351), rather than randomly initialized (competition score 0.211) CNN encoder layer. These results show the potential benefits of leveraging unlabeled data to boost task-specific performance of predictive EEG models.
Collapse
|
24
|
Blette BS, Moutchia J, Al-Naamani N, Ventetuolo CE, Cheng C, Appleby D, Urbanowicz RJ, Fritz J, Mazurek JA, Li F, Kawut SM, Harhay MO. Is low-risk status a surrogate outcome in pulmonary arterial hypertension? An analysis of three randomised trials. THE LANCET. RESPIRATORY MEDICINE 2023; 11:873-882. [PMID: 37230098 PMCID: PMC10592525 DOI: 10.1016/s2213-2600(23)00155-8] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/02/2023] [Revised: 04/19/2023] [Accepted: 04/20/2023] [Indexed: 05/27/2023]
Abstract
BACKGROUND Targeting short-term improvements in multicomponent risk scores for mortality in patients with pulmonary arterial hypertension (PAH) could result in improved long-term outcomes. We aimed to determine whether PAH risk scores were adequate surrogates for clinical worsening or mortality outcomes in PAH randomised clinical trials (RCTs). METHODS We performed an individual participant data meta-analysis of RCTs selected from PAH trials provided by the US Food and Drug Administration (FDA). We calculated predicted risk using the COMPERA, COMPERA 2.0, non-invasive FPHR, REVEAL 2.0, and REVEAL Lite 2 risk scores. The primary outcome of interest was time to clinical worsening, a composite endpoint composed of any of the following events: all-cause death, hospitalisation for worsening PAH, lung transplantation, atrial septostomy, discontinuation of study treatment (or study withdrawal) for worsening PAH, initiation of parenteral prostacyclin analogue therapy, or decrease of at least 15% in 6-min walk distance from baseline, combined with either worsening of WHO functional class from baseline or the addition of an approved PAH treatment. The secondary outcome of interest was time to all-cause mortality. We assessed the surrogacy of these risk scores, parameterised as attainment of low-risk status by 16 weeks, for improvement in long-term clinical worsening and survival using mediation and meta-analysis frameworks. FINDINGS Of 28 trials received from the FDA, three RCTs (AMBITION, GRIPHON, and SERAPHIN; n=2508) had the data necessary to assess long-term surrogacy. The mean age was 49 years (SD 16), 1956 (78%) participants were women, 1704 (68%) were classified as White, and 280 (11%) were Hispanic or Latino. 1388 (55%) of 2503 participants with available data had idiopathic PAH and 776 (31%) of 2503 had PAH associated with connective tissue disease. In a mediation analysis, the proportions of treatment effects explained by attainment of low-risk status ranged only from 7% to 13%. In a meta-analysis of trial-regions, the treatment effects on low-risk status were not predictive of the treatment effects on time to clinical worsening (R2 values 0·01-0·19) nor the treatment effects on time to all-cause mortality (R2 values 0-0·2). A leave-one-out analysis suggested that the use of these risk scores as surrogates might lead to biased inferences regarding the effect of therapies on clinical outcomes in PAH RCTs. Results were similar when using absolute risk scores at 16 weeks as the potential surrogates. INTERPRETATION Multicomponent risk scores have utility for the prediction of outcomes in patients with PAH. Clinical surrogacy for long-term outcomes cannot be inferred from observational studies of outcomes. Our analyses of three PAH trials with long-term follow-up suggest that further study is necessary before using these or other scores as surrogate outcomes in PAH RCTs or clinical care. FUNDING Cardiovascular Medical Research and Education Fund, US National Institutes of Health.
Collapse
|
25
|
Scott JV, Moutchia J, McClelland RL, Al-Naamani N, Weinberg E, Palevsky HI, Minhas J, Appleby DK, Smith A, Pugliese SC, Ventetuolo CE, Kawut SM. Novel Liver Injury Phenotypes and Outcomes in Pulmonary Arterial Hypertension. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.09.28.23296316. [PMID: 37808731 PMCID: PMC10557839 DOI: 10.1101/2023.09.28.23296316] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/10/2023]
Abstract
Background Pulmonary arterial hypertension (PAH) and chronic thromboembolic pulmonary hypertension (CTEPH) are disorders of the pulmonary vasculature that cause right ventricular dysfunction. Systemic consequences of right ventricular dysfunction include damage to other solid organs, such as the liver. However, the profiles and consequences of hepatic injury due to PAH and CTEPH have not been well-studied. Methods We aimed to identify underlying patterns of liver injury in a cohort of PAH and CTEPH patients enrolled in 15 randomized clinical trials conducted between 1998 and 2012. We used unsupervised machine learning to identify liver injury clusters in 13 trials and validated the findings in two additional trials. We then determined whether these liver injury clusters were associated with clinical outcomes or treatment effect heterogeneity. Results Our training dataset included 4,219 patients and our validation dataset included 1,756 patients with complete liver laboratory panels (serum total bilirubin, alkaline phosphatase, aspartate aminotransferase, alanine aminotransferase, and albumin). Using k-means clustering paired with factor analysis, we identified four unique liver phenotypes (no liver injury, hepatocellular injury, cholestatic injury, and combined injury patterns). Patients in the cholestatic injury liver cluster had the shortest time to clinical worsening and highest chance of worsening World Health Organization functional class. Randomization to the experimental arm was associated with a transition to healthier liver clusters compared to randomization to the control arm. The cholestatic injury group experienced the greatest placebo-corrected treatment benefit in terms of six-minute walk distance. Conclusions Liver injury patterns were associated with adverse outcomes in patients with PAH and CTEPH. Randomization to active treatment of pulmonary hypertension in these clinical trials had beneficial effects on liver health compared to placebo. The independent role of liver disease (often subclinical) in determining outcomes warrants prospective studies of the clinical utility of liver phenotyping for PAH prognosis and contribution to clinical disease.
Collapse
|