Derivation, external and clinical validation of a deep learning approach for detecting intracranial hypertension.

Increased intracranial pressure (ICP) ≥15 mmHg is associated with adverse neurological outcomes, but needs invasive intracranial monitoring. Using the publicly available MIMIC-III Waveform Database (2000-2013) from Boston, we developed an artificial intelligence-derived biomarker for elevated ICP (aICP) for adult patients. aICP uses routinely collected extracranial waveform data as input, reducing the need for invasive monitoring. We externally validated aICP with an independent dataset from the Mount Sinai Hospital (2020-2022) in New York City. The AUROC, accuracy, sensitivity, and specificity on the external validation dataset were 0.80 (95% CI, 0.80-0.80), 73.8% (95% CI, 72.0-75.6%), 73.5% (95% CI 72.5-74.5%), and 73.0% (95% CI, 72.0-74.0%), respectively. We also present an exploratory analysis showing aICP predictions are associated with clinical phenotypes. A ten-percentile increment was associated with brain malignancy (OR = 1.68; 95% CI, 1.09-2.60), intracerebral hemorrhage (OR = 1.18; 95% CI, 1.07-1.32), and craniotomy (OR = 1.43; 95% CI, 1.12-1.84; P < 0.05 for all).

Derivation, External Validation and Clinical Implications of a deep learning approach for intracranial pressure estimation using non-cranial waveform measurements.

Importance: Increased intracranial pressure (ICP) is associated with adverse neurological outcomes, but needs invasive monitoring. Objective: Development and validation of an AI approach for detecting increased ICP (aICP) using only non-invasive extracranial physiological waveform data. Design: Retrospective diagnostic study of AI-assisted detection of increased ICP. We developed an AI model using exclusively extracranial waveforms, externally validated it and assessed associations with clinical outcomes. Setting: MIMIC-III Waveform Database (2000-2013), a database derived from patients admitted to an ICU in an academic Boston hospital, was used for development of the aICP model, and to report association with neurologic outcomes. Data from Mount Sinai Hospital (2020-2022) in New York City was used for external validation. Participants: Patients were included if they were older than 18 years, and were monitored with electrocardiograms, arterial blood pressure, respiratory impedance plethysmography and pulse oximetry. Patients who additionally had intracranial pressure monitoring were used for development (N=157) and external validation (N=56). Patients without intracranial monitors were used for association with outcomes (N=1694). Exposures: Extracranial waveforms including electrocardiogram, arterial blood pressure, plethysmography and SpO2. Main Outcomes and Measures: Intracranial pressure > 15 mmHg. Measures were Area under receiver operating characteristic curves (AUROCs), sensitivity, specificity, and accuracy at threshold of 0.5. We calculated odds ratios and p-values for phenotype association. Results: The AUROC was 0.91 (95% CI, 0.90-0.91) on testing and 0.80 (95% CI, 0.80-0.80) on external validation. aICP had accuracy, sensitivity, and specificity of 73.8% (95% CI, 72.0%-75.6%), 99.5% (95% CI 99.3%-99.6%), and 76.9% (95% CI, 74.0-79.8%) on external validation. A ten-percentile increment was associated with stroke (OR=2.12; 95% CI, 1.27-3.13), brain malignancy (OR=1.68; 95% CI, 1.09-2.60), subdural hemorrhage (OR=1.66; 95% CI, 1.07-2.57), intracerebral hemorrhage (OR=1.18; 95% CI, 1.07-1.32), and procedures like percutaneous brain biopsy (OR=1.58; 95% CI, 1.15-2.18) and craniotomy (OR = 1.43; 95% CI, 1.12-1.84; P < 0.05 for all). Conclusions and Relevance: aICP provides accurate, non-invasive estimation of increased ICP, and is associated with neurological outcomes and neurosurgical procedures in patients without intracranial monitoring.

Neighborhood Childhood Opportunity, Race/Ethnicity, and Surgical Outcomes in Children With Congenital Heart Disease.

BACKGROUND: Racial and ethnic disparities in outcomes for children with congenital heart disease (CHD) coexist with disparities in educational, environmental, and economic opportunity. OBJECTIVES: We sought to determine the associations between childhood opportunity, race/ethnicity, and pediatric CHD surgery outcomes. METHODS: Pediatric Health Information System encounters aged <18 years from 2016 to 2022 with International Classification of Diseases-10th edition codes for CHD and cardiac surgery were linked to ZIP code-level Childhood Opportunity Index (COI), a score of neighborhood educational, environmental, and socioeconomic conditions. The associations of race/ethnicity and COI with in-hospital surgical death were modeled with generalized estimating equations and formal mediation analysis. Neonatal survival after discharge was modeled by Cox proportional hazards. RESULTS: Of 54,666 encounters at 47 centers, non-Hispanic Black (Black) (OR: 1.20; P = 0.01), Asian (OR: 1.75; P < 0.001), and Other (OR: 1.50; P < 0.001) groups had increased adjusted mortality vs non-Hispanic Whites. The lowest COI quintile had increased in-hospital mortality in unadjusted and partially adjusted models (OR: 1.29; P = 0.004), but not fully adjusted models (OR: 1.14; P = 0.13). COI partially mediated the effect of race/ethnicity on in-hospital mortality between 2.6% (P = 0.64) and 16.8% (P = 0.029), depending on model specification. In neonatal multivariable survival analysis (n = 13,987; median follow-up: 0.70 years), the lowest COI quintile had poorer survival (HR: 1.21; P = 0.04). CONCLUSIONS: Children in the lowest COI quintile are at risk for poor outcomes after CHD surgery. Disproportionally increased mortality in Black, Asian, and Other populations may be partially mediated by COI. Targeted investment in low COI neighborhoods may improve outcomes after hospital discharge. Identification of unmeasured factors to explain persistent risk attributed to race/ethnicity is an important area of future exploration.

Criteria for Early Pacemaker Implantation in Patients With Postoperative Heart Block After Congenital Heart Surgery.

BACKGROUND: Guidelines recommend observation for atrioventricular node recovery until postoperative days (POD) 7 to 10 before permanent pacemaker placement (PPM) in patients with heart block after congenital cardiac surgery. To aid in surgical decision-making for early PPM, we established criteria to identify patients at high risk of requiring PPM. METHODS: We reviewed all cases of second degree and complete heart block (CHB) on POD 0 from August 2009 through December 2018. A decision tree model was trained to predict the need for PPM amongst patients with persistent CHB and prospectively validated from January 2019 through March 2021. Separate models were developed for all patients on POD 0 and those without recovery by POD 4. RESULTS: Of the 139 patients with postoperative heart block, 68 required PPM. PPM was associated with older age (3.2 versus 1.0 years; P=0.018) and persistent CHB on POD 0 (versus intermittent CHB or second degree heart block; 87% versus 58%; P=0.001). Median days [IQR] to atrioventricular node recovery was 2 [0-5] and PPM was 9 [6-11]. Of the 100 cases of persistent CHB (21 in the validation cohort), 59 (59%) required PPM. A decision tree model identified 4 risk factors for PPM in patients with persistent CHB: (1) aortic valve replacement, subaortic stenosis repair, or Konno procedure; (2) ventricular L-looping; (3) atrioventricular valve replacement; (4) and absence of preoperative antiarrhythmic agent (in POD 0 model only). The POD 4 model specificity was 0.89 [0.67-0.99] and positive predictive value was 0.94 [95% CI 0.81-0.98], which was stable in prospective validation (positive predictive value 1.0). CONCLUSIONS: A data-driven analysis led to actionable criteria to identify patients requiring PPM. Patients with left ventricular outflow tract surgery, atrioventricular valve replacement, or ventricular L-Looping could be considered for PPM on POD 4 to reduce risks of temporary pacing and improve care efficiency.

Impact of institutional routine surveillance endomyocardial biopsy frequency in the first year on rejection and graft survival in pediatric heart transplantation.

BACKGROUND: Routine surveillance biopsy (RSB) is performed to detect asymptomatic acute rejection (AR) after heart transplantation (HT). Variation in pediatric RSB across institutions is high. We examined center-based variation in RSB and its relationship to graft loss, AR, coronary artery vasculopathy (CAV), and cost of care during the first year post-HT. METHODS: We linked the Pediatric Health Information System (PHIS) and Scientific Registry of Transplant Recipients (SRTR, 2002-2016), including all primary-HT aged 0-21 years. We characterized centers by RSB frequency (defined as median biopsies performed among recipients aged ≥12 months without rejection in the first year). We adjusted for potential confounders and center effects with mixed-effects regression analysis. RESULTS: We analyzed 2867 patients at 29 centers. After adjusting for patient and center differences, increasing RSB frequency was associated with diagnosed AR (OR 1.15 p = 0.004), a trend toward treated AR (OR 1.09 p = 0.083), and higher hospital-based cost (US$390 315 vs. $313 248, p < 0.001) but no difference in graft survival (HR 1.00, p = 0.970) or CAV (SHR 1.04, p = 0.757) over median follow-up 3.9 years. Center RSB-frequency threshold of ≥2/year was associated with increased unadjusted rates of treated AR, but no association was found at thresholds greater than this. CONCLUSION: Center RSB frequency is positively associated with increased diagnosis of AR at 1 year post-HT. Graft survival and CAV appear similar at medium-term follow-up. We speculate that higher frequency RSB centers may have increased detection of clinically less important AR, though further study of the relationship between center RSB frequency and differences in treated AR is necessary.

Prediction of the 1-Year Risk of Incident Lung Cancer: Prospective Study Using Electronic Health Records from the State of Maine.

BACKGROUND: Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate. OBJECTIVE: The aim of this study was to develop and validate a prospective risk prediction model to identify patients at risk of new incident lung cancer within the next 1 year in the general population. METHODS: Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. The study population consisted of patients with at least one EHR between April 1, 2016, and March 31, 2018, who had no history of lung cancer. A retrospective cohort (N=873,598) and a prospective cohort (N=836,659) were formed for model construction and validation. An Extreme Gradient Boosting (XGBoost) algorithm was adopted to build the model. It assigned a score to each individual to quantify the probability of a new incident lung cancer diagnosis from October 1, 2016, to September 31, 2017. The model was trained with the clinical profile in the retrospective cohort from the preceding 6 months and validated with the prospective cohort to predict the risk of incident lung cancer from April 1, 2017, to March 31, 2018. RESULTS: The model had an area under the curve (AUC) of 0.881 (95% CI 0.873-0.889) in the prospective cohort. Two thresholds of 0.0045 and 0.01 were applied to the predictive scores to stratify the population into low-, medium-, and high-risk categories. The incidence of lung cancer in the high-risk category (579/53,922, 1.07%) was 7.7 times higher than that in the overall cohort (1167/836,659, 0.14%). Age, a history of pulmonary diseases and other chronic diseases, medications for mental disorders, and social disparities were found to be associated with new incident lung cancer. CONCLUSIONS: We retrospectively developed and prospectively validated an accurate risk prediction model of new incident lung cancer occurring in the next 1 year. Through statistical learning from the statewide EHR data in the preceding 6 months, our model was able to identify statewide high-risk patients, which will benefit the population health through establishment of preventive interventions or more intensive surveillance.

Increased mortality, morbidities, and costs after heart transplantation in heterotaxy syndrome and other complex situs arrangements.

OBJECTIVES: Identify pediatric heart transplant (HT) recipients with heterotaxy and other complex arrangements of cardiac situs (heterotaxy/situs anomaly) and compare mortality, morbidities, length of stay (LOS), and costs to recipients with congenital heart disease without heterotaxy/situs anomaly. METHODS: Using linked registry data (2001-2016), we identified 186 HT recipients with heterotaxy/situs anomaly and 1254 with congenital heart disease without heterotaxy/situs anomaly. We compared post-HT outcomes in univariable and multivariable time-to-event analyses. LOS and cost from HT to discharge were compared using Wilcoxon rank-sum tests. Sensitivity analyses were performed using stricter heterotaxy/situs anomaly group inclusion criteria and through propensity matching. RESULTS: HT recipients with heterotaxy/situs anomaly were older (median age, 5.1 vs 1.6 years; P < .001) and more often black, Asian, Hispanic, or "other" nonwhite (54% vs 32%; P < .001). Heterotaxy/situs anomaly was independently associated with increased mortality (hazard ratio, 1.58; 95% confidence interval, 1.19-2.09; P = .002), even among 6-month survivors (hazard ratio, 1.86; 95% confidence interval, 1.09-3.16; P = .021). Heterotaxy/situs anomaly recipients more commonly required dialysis (odds ratio, 2.58; 95% confidence interval, 1.51-4.42; P = .001) and cardiac reoperation (odds ratio, 1.91; 95% confidence interval, 1.17-3.11; P = .010) before discharge. They had longer ischemic times (19.2 additional minutes [range, 10.9-27.5 minutes]; P < .001), post-HT intensive care unit LOS (16 vs 13 days; P = .012), and hospital LOS (26 vs 23 days; P = .005). Post-HT hospitalization costs were also greater ($447,604 vs $379,357; P = .001). CONCLUSIONS: Heterotaxy and other complex arrangements of cardiac situs are associated with increased mortality, postoperative complications, LOS, and costs after HT. Although increased surgical complexity can account for many of these differences, inferior late survival is not well explained and deserves further study.

Loss of Id3 increases VCAM-1 expression, macrophage accumulation, and atherogenesis in Ldlr-/- mice.

OBJECTIVE: Inhibitor of differention-3 (Id3) promotes B cells homing to the aorta and atheroprotection in Apoe(-/-) mice. We sought to determine the impact of loss of Id3 in the Ldlr((-/-)) mouse model of diet-induced atherosclerosis and identify novel Id3 targets in the vessel wall. METHODS AND RESULTS: Ex vivo optical imaging confirmed that Id3((-/-)) Ldlr((-/-)) mice have significantly fewer aortic B cells than Id3((+/+)) Ldlr(-/-) mice. After 8 and 16 weeks of Western diet, Id3((-/-)) Ldlr((-/-)) mice developed significantly more atherosclerosis than Id3((+/+)) Ldlr((-/-)) mice, with Id3(+/-) Ldlr(-/-) mice demonstrating an intermediate phenotype. There were no differences in serum lipid levels between genotypes. Immunostaining demonstrated that aortas from Id3((-/-)) Ldlr((-/-)) mice had greater intimal macrophage density and C-C chemokine ligand 20 and vascular cell adhesion molecule 1 (VCAM-1) expression compared with Id3((+/+)) Ldlr(-/-) mice. Real-time polymerase chain reaction demonstrated increased VCAM-1 mRNA levels in the aortas of Id3(-/-) Ldlr(-/-) mice. Primary vascular smooth muscle cells from Id3((-/-)) mice expressed greater amounts of VCAM-1 protein compared with control. Gain and loss of function studies in primary vascular smooth muscle cells identified a role for Id3 in repressing VCAM-1 promoter activation. Chromatin immunoprecipitation demonstrated interaction of E12 with the VCAM-1 promoter, which is inhibited by Id3. CONCLUSIONS: Id3 is an atheroprotective transcription regulator with targets in both B cells and vessel wall cells leading to reduced macrophage accumulation and reduced atherosclerosis formation.