Simple Clinical Variables Research Articles

Risk stratification for a primary prevention ICD: Performance of the MADIT-ICD Benefit Score in contemporary real world patients

Abstract Background We have recently developed the MADIT-ICD Benefit Score to improve risk stratification for primary implantable cardioverter defibrillator (ICD) implantation by assessing the competing risk of life-threatening ventricular tachyarrhythmia (VTA) vs. non-arrhythmic mortality based using simple clinical variables. Patients with a MADIT-ICD Benefit Score of < 50 are more likely to experience non-arrhythmic mortality than life-threatening VTA, and therefore derive limited benefit from a prophylactic ICD. Purpose We aimed to provide data on the performance of the MADIT-ICD Benefit Score in a real world population, comprising patients with HFrEF and either ischemic or nonischemic cardiomyopathy (ICM/NICM) who are treated with contemporary guideline-directed medical therapy (GDMT). Methods The study population comprised 2875 patients who were implanted with a primary prevention ICD and prospectively followed in a large tertiary healthcare system (the University of Rochester Medical Center, including 3 affiliated hospitals in Upstate New York) between 2017 through 2023. Arrhythmic events were captured from device interrogation data, which were blindly adjudicated by 2 electrophysiologists. Results Among the 2875 study patients, mean age was 62 ± 15 years, 1265 (44%) were women, and 1667 (58%) had ICM. Guideline-directed medical therapies, including angiotensin-converting enzyme inhibitors or angiotensin receptor blockers, angiotensin receptor/neprilysin inhibitors, beta-blockers, mineralocorticoid receptor antagonists, and sodium-glucose transport protein 2 (SGLT2) inhibitors, were prescribed to 43%, 36%, 96%, 67% and 32% of study patients, respectively. The 2-year cumulative incidence of VTA, after accounting for the competing risk of death, was 19% vs. 11% in patients with a Score of ≥50 vs. <50, respectively (p<0.001; Figure 1A). Findings regarding ICD shocks were consistent (8% vs. 4%, respectively, p<0.001; Figure 1B) The rate of VTA events at 4 years was directly correlated with increasing quartiles of the MADIT-ICD Benefit Score, while the corresponding rates of non-arrhythmic mortality were inversely correlated with score quartiles (Figure 1C). A similar direct correlation with increasing Benefit Score quartiles was observed when the endpoint of ICD shocks was assessed (Figure 1D). Accordingly, the benefit of the ICD (calculated as the difference between predicted rates of VTA/shock events and corresponding rates of non-arrhythmic mortality) was attenuated with decreasing quartiles of the MADIT-ICD Benefit Score (Figures 1C and 1D; right column). Conclusions We show good performance of the MADIT-ICD Benefit Score in a large cohort of real world ICD recipients who are treated with contemporary GDMT. These data support the use of the MADIT-ICD Benefit Score for improved risk stratification and for shared decision-making in contemporary candidates for a primary prevention ICD.

Myocarditis-A Helpful Algorithm to Overcome Diagnostic Challenges in the Pediatric Population.

This study was designed to investigate clinical differences between pediatric patients who presented with chest pain, tachycardia, and/or tachypnea who subsequently were or were not diagnosed with myocarditis. The results were used to develop a decision tree to aid in rapid diagnosis of pediatric myocarditis. A retrospective case-control study was performed using the electronic medical records of children aged 0 to 18 years between the years 2003 and 2020 with a complaint of chest pain, tachycardia, and/or tachypnea. Patients included in the study were those diagnosed with myocarditis and those with suspected myocarditis, which was ultimately ruled out. Demographic and clinical differences between the research groups were analyzed. A decision tree was rendered using the rpart (Recursive Partitioning and Regression Trees) package. Four thousand one hundred twenty-five patients were screened for eligibility. Seventy-three myocarditis patients and 292 nonmyocarditis patients were included. Compared with the control group, the study group was found to have a higher mean respiratory rate (37 ± 23 vs 23 ± 7 breaths per minute) and mean heart rate (121 ± 44 vs 97 ± 25 beats per minute) and lower mean systolic and diastolic blood pressure (102 ± 27/56 ± 17 mm Hg vs 114 ± 14/67 ± 10 mm Hg). The mean white blood cell count was greater in the case group (13 ± 6 vs 10 ± 5 × 10 3 /μL). A decision tree was rendered using simple demographic and clinical variables. The accuracy of the algorithm was 85.2%, with 100% accuracy in patients aged 0 to 2.5 years and 69% in patients aged 2.5 to 18 years. The clinical and laboratory characteristics described in this study were similar to what is described in the literature. The decision tree may aid in the diagnosis of myocarditis in patients 2.5 years and younger. In the population aged 2.5 to 18 years, the decision tree did not constitute an adequate tool for detecting myocarditis.

Predicting solute transfer rate in patients initiating peritoneal dialysis

BackgroundWhile assessment of membrane characteristics is fundamental to peritoneal dialysis (PD) prescription in patients initiating therapy, peritoneal equilibration test has theoretical and practical drawbacks. We wished to determine whether an equation using simple clinical variables could predict fast (above population mean) peritoneal solute transfer rate without dialysate sampling.MethodsWe measured peritoneal solute transfer rate, as determined by peritoneal equilibration test using the 4-h dialysate to plasma creatinine ratio, in consecutive PD outpatients attending a single tertiary hospital for their first clinical follow-up within 3 months of dialysis initiation. An equation estimating peritoneal solute transfer rate based on readily available clinical variables was generated in a randomly selected modeling group and tested in a distinct validation group.ResultsWe included 712 patients, with 562 in the modeling group and 150 in the validation group. Mean age was 58.4 ± 15.9 with 431 (60.5%) men. Mean peritoneal solute transfer rate value was 0.73 ± 0.13. An equation based on gender, race, serum sodium and albumin yielded a receiving operator characteristics (ROC) area under the curve (AUC) to detect fast peritoneal solute transfer rate (> 0.73) of 0.74 (0.67–0.82). Estimated peritoneal solute transfer rate values based on percentiles 15th (> 0.66), 20th (> 0.68), 25th (> 0.69) and 30th (> 0.70) could rule out fast peritoneal solute transfer rate with negative predictive values of 100%, 93.5%, 84.2% and 80.0%, respectively.ConclusionsAn equation based on simple clinical variables allows ruling out fast transport in a significant proportion of patients initiating PD with a high degree of confidence without requiring dialysate sampling. This could prove useful in guiding dialysis prescription of PD patients in daily clinical practice, particularly in low-resource settings.Graphical abstract

Analysis of type 2 diabetes heterogeneity with a tree-like representation: insights from the prospective German Diabetes Study and the LURIC cohort

Heterogeneity in type 2 diabetes can be represented by a tree-like graph structure by use of reversed graph-embedded dimensionality reduction. We aimed to examine whether this approach can be used to stratify key pathophysiological components and diabetes-related complications during longitudinal follow-up of individuals with recent-onset type 2 diabetes. For this cohort analysis, 927 participants aged 18-69 years from the German Diabetes Study (GDS) with recent-onset type 2 diabetes were mapped onto a previously developed two-dimensional tree based on nine simple clinical and laboratory variables, residualised for age and sex. Insulin sensitivity was assessed by a hyperinsulinaemic-euglycaemic clamp, insulin secretion was assessed by intravenous glucose tolerance test, hepatic lipid content was assessed by 1 H magnetic resonance spectroscopy, serum interleukin (IL)-6 and IL-18 were assessed by ELISA, and peripheral and autonomic neuropathy were assessed by functional and clinical measures. Participants were followed up for up to 16 years. We also investigated heart failure and all-cause mortality in 794 individuals with type 2 diabetes undergoing invasive coronary diagnostics from the Ludwigshafen Risk and Cardiovascular Health (LURIC) cohort. There were gradients of clamp-measured insulin sensitivity (both dimensions: p<0·0001) and insulin secretion (pdim1<0·0001, pdim2=0·00097) across the tree. Individuals in the region with the lowest insulin sensitivity had the highest hepatic lipid content (n=205, pdim1<0·0001, pdim2=0·037), pro-inflammatory biomarkers (IL-6: n=348, pdim1<0·0001, pdim2=0·013; IL-18: n=350, pdim1<0·0001, pdim2=0·38), and elevated cardiovascular risk (nevents=143, pdim1=0·14, pdim2<0·00081), whereas individuals positioned in the branch with the lowest insulin secretion were more prone to require insulin therapy (nevents=85, pdim1=0·032, pdim2=0·12) and had the highest risk of diabetic sensorimotor polyneuropathy (nevents=184, pdim1=0·012, pdim2=0·044) and cardiac autonomic neuropathy (nevents=118, pdim1=0·0094, pdim2=0·06). In the LURIC cohort, all-cause mortality was highest in the tree branch showing insulin resistance (nevents=488, pdim1=0·12, pdim2=0·0032). Significant gradients differentiated individuals having heart failure with preserved ejection fraction from those who had heart failure with reduced ejection fraction. These data define the pathophysiological underpinnings of the tree structure, which has the potential to stratify diabetes-related complications on the basis of routinely available variables and thereby expand the toolbox of precision diabetes diagnosis. German Diabetes Center, German Federal Ministry of Health, Ministry of Culture and Science of the state of North Rhine-Westphalia, German Federal Ministry of Education and Research, German Diabetes Association, German Center for Diabetes Research, European Community, German Research Foundation, and Schmutzler Stiftung.

Using simple clinical and ultrasound variables to develop a model to predict first trimester pregnancy viability

IntroductionEarly prediction of pregnancies destined to miscarry will allow couples to prepare for this common but often unexpected eventuality, and clinicians to allocate finite resources. We aimed to develop a prediction model combining clinical, demographic, and sonographic data as a clinical tool to aid counselling about first trimester pregnancy outcome. Material and methodsThis is a prospective, observational cohort study conducted at Queen Charlotte’s and Chelsea Hospital, UK from March 2014 to May 2019. Women with confirmed intrauterine pregnancies between 5 weeks and their dating scan (11–14 weeks) were recruited. Participants attended serial ultrasound scans in the first trimester and at each visit recorded symptoms of vaginal bleeding, pelvic pain, nausea and vomiting using validated scoring tools. Pregnancies were followed up until the dating scan (11–14 weeks). Univariate and multivariate analyses were performed to predict first trimester viability. A model was developed with multivariable logistic regression, variables limited by feature selection, and bootstrapping with multiple imputation was used for internal validation. Results1403 women were recruited and after exclusions, data were available for 1105. 160 women (14.5 %) experienced first trimester miscarriage and 945 women (85.5 %) had viable pregnancies at 11–14 weeks’ gestation. The average gestational age at the initial visit (calculated from the menstrual dates) was 7 + 1 weeks (+/-12.2 days). A multivariable logistic regression model was developed to predict first trimester viability and included the variables: mean gestational sac diameter, presence of fetal heart pulsations, difference in gestational age from last menstrual period and from mean sac diameter on ultrasonography, current folic acid usage and maternal age. The model demonstrated good performance (optimism-corrected area under curve (AUC) 0.84, 95 % CI 0.81–0.87; optimism-corrected calibration slope 0.969). ConclusionWe have developed and internally validated a model to predict first trimester viability with good accuracy prior to the 11–14 week dating scan, which now needs to be externally validated prior to clinical use.

Prediction of incident heart failure through deep learning-based analysis of 1-lead ECGs

Abstract Background/Introduction Identification of individuals at risk for heart failure (HF) can lead to early intervention. However, large scale screening for incident HF in the general population is insufficient, partly due to the limited capacities in health care systems and number of health care specialists. One-lead ECGs, e.g. from wearables capable of deriving this biomarker, are becoming more popular in the population. This holds the potential to identify individuals at risk who could benefit from a referral to a HF specialist. Purpose We examined the ability to predict three-year HF incidence from 1-lead ECGs using a deep learning (DL) model that was trained on data from the UK Biobank (UKB). Methods The UKB was established in 2006 and contains data from 500,000 participants from the British general population. N = 100,551 1-lead ECGs from 91,898 unique participants were used for this study. This includes 57,897 3-lead resting ECGs written during ergometry exams between 2006 and 2010 (Exam 1; median age 56.7 years, 46.2% men) and at the first follow-up from 2010-2013 (Exam 2; median age 61.3 years, 49% men) and 32,828 12-lead resting ECGs which were acquired between 2014 and 2020 (Exam 3; median age 63.5 years, 48.4% men). Lead I was extracted from the ECGs for all analyses. A 1D-Convolutional Neural Network was used for prediction of the 3-year risk of incident HF. A comparison with the CHARGE-AF score was performed using a nested 6-fold cross-validation scheme. The models were evaluated using the Area Under the Curve (AUC). Results In all three exams, the DL model was able to reliably detect 3-year incident HF (AUC; Exam 1: 0.738, Exam 2: 0.822, Exam 3: 0.738) while the CHARGE-AF score provided slightly better predictions at Exam 1 and Exam 3 (AUC 0.766, 0.748), but lower results in Exam 2 (AUC 0.736). Combining both models led to increased discriminatory properties across all exams (AUC; Exam 1: 0.812, Exam 2: 0.832, Exam 3: 0.788). Conclusion The derived DL model shows high discriminatory ability in the prediction of incident HF from 1-lead ECGs. The predictive ability can be further increased when combined with simple clinical variables from the CHARGE-AF score. This study represents another step towards the application of DL-based analysis of the ECG to advance health care.

Machine-learning score to predict in-hospital outcomes in patients Hospitalized in Intensive Cardiac Care Unit

Abstract Background While few scores are available for risk stratification of patients hospitalized in Intensive Cardiac Care Unit (ICCU) using traditional statistical methods, the potential benefit of machine learning is not established. Purpose To investigate the feasibility and accuracy of machine-learning (ML) to predict in-hospital major adverse events (MAE) in patients hospitalized in ICCU and compare its performance with existing scores. Methods From April 7 to 22, 2021, a French nationwide, multicenter, prospective, study involving 39 centers included all consecutive patients admitted in ICCU (N=1499). The primary outcome was in-hospital MAE defined as a composite outcome including all-cause in-hospital mortality, cardiogenic shock and resuscitated cardiac arrest (severe ventricular arrhythmia requiring defibrillation or anti-arrhythmic agents). Twenty-eight clinical, biological, ECG, and echocardiographic variables were considered for the Boruta variable selection algorithm. Using 31 centers randomly as an index cohort, several ML algorithms (logistic regression, ridge regression, boosted cost-sensitive C5.0 and XGBoost. C5.0 ) were evaluated to build a ML-score to predict in-hospital MAE. The other 8 centers formed the external validation cohort of the ML-score. Results Among 1499 consecutive patients included (age 63.3±14.9 years, 69.6% male), 61 had in-hospital MAE (4.3%). Out of 28 variables included in the feature selection, seven were selected as of particular importance to predict MAE in the training set (N=844) including: illicit drug use, mean arterial pressure, Killip stage, exhaled CO level, left ventricular ejection fraction, TAPSE value and peak E/e’ ratio. Boosted cost-sensitive C5.0 technique showed the best performance compared with other ML-techniques (area under the curve [AUC]=0.90, PR-AUC=0.57, F1 score=0.5), using 5 of the 7 above mentioned variables: mean arterial pressure, exhaled CO level, left ventricular ejection fraction, TAPSE value and peak E/e’ ratio. Our ML-score exhibited a higher AUC compared with existing scores for MAE prediction (ML score: 0.90 vs TIMI-score: 0.56, GRACE-score: 0.52, Acute HF-score: 0.65; all p&amp;lt;0.001). ML-score also exhibited a good AUC in the external cohort (AUC 0.97). Conclusions Including five simple clinical and echocardiographic variables (mean arterial pressure, exhaled CO level, left ventricular ejection fraction, TAPSE value and peak E/e’ ratio) routinely assessed in patients admitted in ICCU, the ML score exhibited a better prognostic value to predict in-hospital outcomes compared with existing scores.ML model and existing scores: ROC curveML model and existing scores: PR curve

Trends in Atrial Fibrillation Management—Results from a National Multi-Center Urgent Care Network Registry

Background: Atrial fibrillation (AF) is a common diagnosis in patients presenting to urgent care centers (UCCs), yet there is scant research regarding treatment in these centers. While some of these patients are managed within UCCs, some are referred for further care in an emergency department (ED). Objectives: We aimed to identify the rate of patients referred to an ED and define predictors for this outcome. We analyzed the rates of AF diagnosis and hospital referral over the years. Finally, we described trends in patient anticoagulation (AC) medication use. Methods: This retrospective study included 5873 visits of patients over age 18 visiting the TEREM UCC network with a diagnosis of AF over 11 years. Multivariate analysis was used to identify predictors for ED referral. Results: In a multivariate model, predictors of referral to an ED included vascular disease (OR 1.88 (95% CI 1.43–2.45), p &lt; 0.001), evening or night shifts (OR 1.31 (95% CI 1.11–1.55), p &lt; 0.001; OR 1.68 (95% CI 1.32–2.15), p &lt; 0.001; respectively), previously diagnosed AF (OR 0.31 (95% CI 0.26–0.37), p &lt; 0.001), prior treatment with AC (OR 0.56 (95% CI 0.46–0.67), p &lt; 0.001), beta blockers (OR 0.63 (95% CI 0.52–0.76), p &lt; 0.001), and antiarrhythmic medication (OR 0.58 (95% CI 0.48–0.69), p &lt; 0.001). Visits diagnosed with AF increased over the years (p = 0.030), while referrals to an ED decreased over the years (p = 0.050). The rate of novel oral anticoagulant prescriptions increased over the years. Conclusions: The rate of referral to an ED from a UCC over the years is declining but remains high. Referrals may be predicted using simple clinical variables. This knowledge may help to reduce the burden of hospitalizations.

Differential effect of interventions in patients with prediabetesstratified by a machine learning-based diabetes progression prediction model.

To investigate whether stratifying participants with prediabetes according to their diabetes progression risks (PR) could affect their responses to interventions. We developed a machine learning-based model to predict the 1-year diabetes PR (ML-PR) with the least predictors. The model was developed and internally validated in participants with prediabetes in the Pinggu Study (a prospective population-based survey in suburban Beijing; n = 622). Patients from the Beijing Prediabetes Reversion Program cohort (a multicentre randomized control trial to evaluate the efficacy of lifestyle and/or pioglitazone on prediabetes reversion; n = 1936) were stratified to low-, medium- and high-risk groups using ML-PR. Different effect of four interventions within subgroups on prediabetes reversal and diabetes progression was assessed. Using least predictors including fasting plasma glucose, 2-h postprandial glucose after 75 g glucose administration, glycated haemoglobin, high-density lipoprotein cholesterol and triglycerides, and the ML algorithm XGBoost, ML-PR successfully predicted the 1-year progression of participants with prediabetes in the Pinggu study [internal area under the curve of the receiver operating characteristic curve 0.80 (0.72-0.89)] and Beijing Prediabetes Reversion Program [external area under the curve of the receiver operating characteristic curve 0.80 (0.74-0.86)]. In the high-risk group pioglitazone plus intensive lifestyle therapy significantly reduced diabetes progression by about 50% at year l and the end of the trial in the high-risk group compared with conventional lifestyle therapy with placebo. In the medium- or low-risk group, intensified lifestyle therapy, pioglitazone or their combination did not show any benefit on diabetes progression and prediabetes reversion. This study suggests personalized treatment for prediabetes according to their PR is necessary. ML-PR model with simple clinical variables may facilitate personal treatment strategies in participants with prediabetes.

Subgroups of adult-onset diabetes: a data-driven cluster analysis in a Ghanaian population

Adult-onset diabetes mellitus (here: aDM) is not a uniform disease entity. In European populations, five diabetes subgroups have been identified by cluster analysis using simple clinical variables; these may elucidate diabetes aetiology and disease prognosis. We aimed at reproducing these subgroups among Ghanaians with aDM, and establishing their importance for diabetic complications in different health system contexts. We used data of 541 Ghanaians with aDM (age: 25–70 years; male sex: 44%) from the multi-center, cross-sectional Research on Obesity and Diabetes among African Migrants (RODAM) Study. Adult-onset DM was defined as fasting plasma glucose (FPG) ≥ 7.0 mmol/L, documented use of glucose-lowering medication or self-reported diabetes, and age of onset ≥ 18 years. We derived subgroups by cluster analysis using (i) a previously published set of variables: age at diabetes onset, HbA1c, body mass index, HOMA-beta, HOMA-IR, positivity of glutamic acid decarboxylase autoantibodies (GAD65Ab), and (ii) Ghana-specific variables: age at onset, waist circumference, FPG, and fasting insulin. For each subgroup, we calculated the clinical, treatment-related and morphometric characteristics, and the proportions of objectively measured and self-reported diabetic complications. We reproduced the five subgroups: cluster 1 (obesity-related, 73%) and cluster 5 (insulin-resistant, 5%) with no dominant diabetic complication patterns; cluster 2 (age-related, 10%) characterized by the highest proportions of coronary artery disease (CAD, 18%) and stroke (13%); cluster 3 (autoimmune-related, 5%) showing the highest proportions of kidney dysfunction (40%) and peripheral artery disease (PAD, 14%); and cluster 4 (insulin-deficient, 7%) characterized by the highest proportion of retinopathy (14%). The second approach yielded four subgroups: obesity- and age-related (68%) characterized by the highest proportion of CAD (9%); body fat-related and insulin-resistant (18%) showing the highest proportions of PAD (6%) and stroke (5%); malnutrition-related (8%) exhibiting the lowest mean waist circumference and the highest proportion of retinopathy (20%); and ketosis-prone (6%) with the highest proportion of kidney dysfunction (30%) and urinary ketones (6%). With the same set of clinical variables, the previously published aDM subgroups can largely be reproduced by cluster analysis in this Ghanaian population. This method may generate in-depth understanding of the aetiology and prognosis of aDM, particularly when choosing variables that are clinically relevant for the target population.

Risk prediction of preoperative acute ischemic stroke in acute type A aortic dissection.

To predict preoperative acute ischemic stroke (AIS) in acute type A aortic dissection (ATAAD). In this multi-center retrospective study, 508 consecutive patients diagnosed as ATAAD between April 2020 and March 2021 were considered for inclusion. The patients were divided into a development cohort and two validation cohorts based on time periods and centers. Clinical data and imaging findings obtained were analyzed. Univariable and multivariable logistic regression analyses were performed to identify predictors associated with preoperative AIS. The performance of resulting nomogram was evaluated in discrimination and calibration on all cohorts. A total of 224 patients were in the development cohort, 94 in the temporal validation cohort, and 118 in the geographical validation cohort. Six predictors were identified: age, syncope, D-dimer, moderate to severe aortic valve insufficiency, diameter ratio of true lumen in ascending aorta < 0.33, and common carotid artery dissection. The nomogram established showed good discrimination (area under the receiver operating characteristic curve [AUC], 0.803; 95% CI: 0.742, 0.864) and calibration (Hosmer-Lemeshow test p = 0.300) in the development cohort. External validation showed good discrimination and calibration abilities in both temporal (AUC, 0.778; 95% CI: 0.671, 0.885; Hosmer-Lemeshow test p = 0.161) and geographical cohort (AUC, 0.806; 95% CI: 0.717, 0.895; Hosmer-Lemeshow test p = 0.100). A nomogram, based on simple imaging and clinical variables collected on admission, showed good discrimination and calibration abilities in predicting preoperative AIS for ATAAD patients. • A nomogram based on simple imaging and clinical findings may predict preoperative acute ischemic stroke in patients with acute type A aortic dissection in emergencies. • The nomogram showed good discrimination and calibration abilities in validation cohorts.

Deep Learning Approaches for Glioblastoma Prognosis in Resource-Limited Settings: A Study Using Basic Patient Demographic, Clinical, and Surgical Inputs

Glioblastoma (GBM) is the most common brain tumor in the United States, with an annual incidence rate of 3.21 per 100,000. It is the most aggressive type of diffuse glioma and has a median survival of months after treatment. This study aims to assess the accuracy of different novel deep learning models trained on a set of simple clinical, demographic, and surgical variables to assist in clinical practice, even in areas with constrained health care infrastructure. Our study included 37,095 patients with GBM from the SEER (Surveillance Epidemiology and End Results) database. All predictors were based on demographic, clinicopathologic, and treatment information of the cases. Our outcomes of interest were months of survival and vital status. Concordance index (C-index) and integrated Brier scores (IBS) were used to evaluate the performance of the models. The patient characteristics and the statistical analyses were consistent with the epidemiologic literature. The models C-index and IBS ranged from 0.6743 to 0.6918 and from 0.0934 to 0.1034, respectively. Probabilistic matrix factorization (0.6918), multitask logistic regression (0.6916), and logistic hazard (0.6916) had the highest C-index scores. The models with the lowest IBS were the probabilistic matrix factorization (0.0934), multitask logistic regression (0.0935), and logistic hazard (0.0936). These models had an accuracy (1-IBS) of 90.66%; 90.65%, and 90.64%, respectively. The deep learning algorithms were deployed on an interactive Web-based tool for practical use available via https://glioblastoma-survanalysis.herokuapp.com/. Novel deep learning algorithms can better predict GBM prognosis than do baseline methods and can lead to more personalized patient care regardless of extensive electronic health record availability.

Developing a triage predictive model for access to a spinal surgeon using clinical variables and natural language processing of radiology reports.

To utilize natural language processing (NLP) of MRI reports and various clinical variables to develop a preliminary model predictive of the need for surgery in patients with low back and neck pain. Such a model would be beneficial for informing clinical practice decisions and help reduce the number of unnecessary surgical referrals, streamlining the surgical process. A historical cohort study was conducted using de-identified data from patients referred to a spine assessment clinic. Various demographic, clinical, and radiological variables were included as potential predictors. Full-text radiology reports of patients' MRI findings were vectorized using NLP before applying machine learning algorithms to develop models predicting who underwent surgery. Outputs from these models were then entered into a logistic regression model with clinical variables to develop a preliminary model predictive of surgical recommendations. Of the 398 patients assessed, 71 underwent spine surgery. NLP variables were significant predictors in univariate analysis but did not remain in the final logistic regression model. An outcome of receiving surgery was predicted by a primary symptom of low back and leg pain (adjusted odds ratio 2.81), distal pain indicated by a pain diagram (adjusted odds ratio 2.49) and self-reported difficulties walking (adjusted odds ratio 2.73). A logistic regression model was created to predict which patients may require spine surgery. Simple clinical variables appeared more predictive than variables created using NLP. However, additional research with more data samples is needed to validate this model and fully evaluate the usefulness of NLP for this task.

Accuracy of screening strategies for masked hypertension: a large-scale nationwide study based on home blood pressure monitoring.

This study compared the ability of guideline-proposed office blood pressure (OBP) screening thresholds [European Society of Hypertension (ESH) guidelines: 130/85 mmHg for individuals with an OBP < 140/90 mmHg; American College of Cardiology/American Heart Association (ACC/AHA) guidelines: 120/75 mmHg for individuals with an OBP < 130/80 mmHg] and novel screening scores to identify normotensive individuals at high risk of having masked hypertension (MH) in an office setting. We cross-sectionally evaluated untreated participants with an OBP < 140/90 mmHg (n = 22,266) and an OBP < 130/80 mmHg (n = 10,005) who underwent home blood pressure monitoring (HBPM) (derivation cohort) from 686 Brazilian sites. MH was defined according to criteria suggested by the ESH (OBP < 140/90 mmHg; HBPM ≥ 135/85 mmHg), Brazilian Society of Cardiology (BSC) (OBP < 140/90 mmHg; HBPM ≥ 130/80 mmHg) and ACC/AHA (OBP < 130/80 mmHg; HBPM ≥ 130/80 mmHg). Scores were generated from multivariable logistic regression coefficients between MH and clinical variables (OBP, age, sex, and BMI). Considering the ESH, BSC, and ACC/AHA criteria, 17.2%, 38.5%, and 21.2% of the participants had MH, respectively. Guideline-proposed OBP screening thresholds yielded area under curve (AUC) values of 0.640 (for ESH criteria), 0.641 (for BSC criteria), and 0.619 (for ACC/AHA criteria) for predicting MH, while scores presented as continuous variables or quartiles yielded AUC values of 0.700 and 0.688 (for ESH criteria), 0.720 and 0.709 (for BSC criteria), and 0.671 and 0.661 (for ACC/AHA criteria), respectively. Further analyses performed with alternative untreated participants (validation cohort; n = 2807 with an OBP < 140/90 mmHg; n = 1269 with an OBP < 130/80 mmHg) yielded similar AUC values. In conclusion, the accuracy of guideline-proposed OBP screening thresholds in identifying individuals at high risk of having MH in an office setting is limited and is inferior to that yielded by scores derived from simple clinical variables.

Determinants and prognostic value of in-hospital infection in patients waiting for permanent pacemaker implantation

BackgroundIn-hospital delays in permanent cardiac pacemaker (PPM) implantation are common and may result in in-hospital infection among patients waiting for PPM implantation (pre-PPM-HI). This study investigated the predictors and prognostic impact of these events. MethodsWe retrospectively evaluated 905 consecutive patients (68.2 ± 16.0 years; 54% males) who underwent PPM implantation. Clinical characteristics, pre-PPM-HI and 30-day mortality were recorded and a risk score for pre-PPM-HI was generated using multivariable logistic regression coefficients. ResultsEigthy-nine patients (10% of the sample) developed pre-PPM-HI. Multivariable logistic regression analysis identified urinary catheter use, complete atrioventricular block, implantation of temporary pacemaker and diabetes mellitus as independent predictors of pre-PPM-HI. The generated score (range 0–10.1) played a better role in predicting pre-PPM-HI than individual factors, yielding an area under the curve [95%CI] of 0.754 [0.705–0.803]. Patients with score ≥ 7.5 had 18-fold greater risk of developing pre-PPM-HI than those with score < 2.5. Furthermore, multivariable Cox-regression analysis showed that patients who developed pre-PPM-HI had greater 30-day mortality after PPM implantation (hazard ratio [95%CI] = 2.90 [1.18–7.16], p = 0.021) compared with their counterparts. ConclusionsThis study reveals that pre-PPM-HI is an independent predictor of early mortality after PPM implantation. In addition, a clinical score developed from simple clinical variables accurately identified patients at high risk of pre-PPM-HI. In scenarios where delays in PPM implantation are unavoidable, such as reference hospitals with high demand, the use of this tool can potentially help in the hierarchy of patients and in the reduction of this adverse event.

Predictors of Septic Shock or Bacteremia in Children Experiencing Febrile Neutropenia Post-Chemotherapy.

Febrile neutropenia (FN) is an early indicator of infection in oncology patients post-chemotherapy. We aimed to determine clinical predictors of septic shock and/or bacteremia in pediatric cancer patients experiencing FN and to create a model that classifies patients as low-risk for these outcomes. This is a retrospective analysis with clinical data of a cohort of pediatric oncology patients admitted during July 2015 to September 2017 with FN. One FN episode per patient was randomly selected. Statistical analyses include distribution analysis, hypothesis testing, and multivariate logistic regression to determine clinical feature association with outcomes. A total of 865 episodes of FN occurred in 429 subjects. In the 404 sampled episodes that were analyzed, 20.8% experienced outcomes of septic shock and/or bacteremia. Gram-negative bacteria count for 70% of bacteremias. Features with statistically significant influence in predicting these outcomes were hematological malignancy (P < .001), cancer relapse (P = .011), platelet count (P = .004), and age (P = .023). The multivariate logistic regression model achieves AUROC = 0.66 (95% CI 0.56-0.76). The optimal classification threshold achieves sensitivity = 0.96, specificity = 0.33, PPV = 0.40, and NPV = 0.95. This model, based on simple clinical variables, can be used to identify patients at low-risk of septic shock and/or bacteremia. The model's NPV of 95% satisfies the priority to avoid discharging patients at high-risk for adverse infection outcomes. The model will require further validation on a prospective population.

Prediction of peritoneal soiling in acute appendicitis with simple clinical and laboratory data. Prospective, multicenter, cohort study of 2,645 adult patients nationwide

Background and aimsIn order to facilitate the preoperative prediction of complicated appendicitis, we propose a complementary approach by selecting an endpoint defined by the intraoperative finding of peritoneal soiling (PS). MethodsOver a 6-month period, 38 centers (5% of all public hospitals) attending emergency general surgery patients on a 24-h, 7-days a week basis, enrolled consecutive adult patients requiring appendectomy. Patients were stratified according to the absence or the finding of PS during the surgical procedure. ResultsA total of 2645 patients were included; median age (IQR) was 35 (22–51) years, 44.3% were female. The laparoscopic approach was used in 70.8% of appendectomies. In a third of patients (31.7%), there was PS with pus around the appendix, or bowel contents, free pus, or blood in the peritoneal cavity. To develop the prediction model, 1764 patients were randomly selected for the derivation cohort and the remaining 881 patients were assigned to the validation cohort. On multivariable logistic regression analysis of all patients, two clinical variables (age, and pulse) and three laboratory variables (serum urea, serum sodium, and white blood cell count) were individually associated (P < .05) with a greater probability of having PS (Hosmer-Lemeshow chi, 1.63; P = .99; C-statistic, 0.7). Based on the multivariable regression model, both static and dynamic nomograms were developed for the prediction of PS in patients with acute appendicitis. ConclusionsThe entry of simple clinical and laboratory variables in the dynamic nomogram may be useful in guiding the initial management of patients with acute appendicitis in resource-limited settings.

Comparison of NAFLD Fibrosis Score with Shear Wave Elastograpghy to Identify Liver Fibrosis in Patients with NAFLD

Introduction: NAFLD is diagnosed by non-invasive and invasive methods. Non-invasive methods include NAFLD fibrosis score, AST/Platelets ratio index (APRI), FIB-4 score, BARD score, USG abdomen, Fibro-scan liver, transient elastography, MRI and MRI with elastography (MRE). Objectives: To determine the frequency of different grades of fibrosis on shear wave elastography in patients with NAFLD and to compare mean NAFLD fibrosis score in different stages of liver fibrosis. Study design: Cross-sectional study. Study duration: 26th February 2021 to 25th August 2021. Settings: Department of Gastroenterology SZH, Lahore. Materials &amp; Methods: A total of 197 patients with NAFLD of age 18-70 years were included. Patients with hepatitis B and/or C infection, hemochromatosis, Wilson’s disease, Alpha 1 antitrypsin deficiency, celiac disease, autoimmune hepatitis, primary biliary cholangitis, primary sclerosing cholangitis were excluded. Hepatic ultrasonographic examination was performed. Blood samples were taken in a 10cc BD syringe and were sent for assessment of PT/INR, LFTs including albumin, platelets count and fasting or random glucose level. Reports were assessed and the NAFLD fibrosis scores were calculated. Shearwave elastography was used as gold standard test for the detection and confirmation of liver fibrosis; and results were compared. Results: Age range in this study was from 18 to 70 years with mean age of 49.30 ± 12.05 years. Majority of the patients 145 (73.60%) were between 41 to 70 years of age. Out of these 197 patients, 80 (40.61%) were males and 117 (59.39%) were females with male to female ratio of 1:1.5. In this study, frequency of different grades of fibrosis on shear wave elastography in patients with NAFLD was as follows; F0 in 44 (22.34%), F1 in 89 (45.18%), F2 in 31 (15.74%), F3 in 22 (11.17%) and F4 in 11 (5.58%) patients. Conclusion: This study concluded that non-invasive NAFLD fibrosis score should be used to rule out the presence or absence of liver fibrosis by using simple clinical and biochemical variables and thus avoid the need of liver biopsy. Keywords: Non-Alcoholic Fatty Liver Disease, Fibrosis Score, Shearwave Elastography

Predicting Parkinson's Disease and Its Pathology via Simple Clinical Variables.

Background:Parkinson’s disease (PD) is a chronic, disabling neurodegenerative disorder.Objective:To predict a future diagnosis of PD using questionnaires and simple non-invasive clinical tests.Methods:Participants in the prospective Kuakini Honolulu-Asia Aging Study (HAAS) were evaluated biannually between 1995–2017 by PD experts using standard diagnostic criteria. Autopsies were sought on all deaths. We input simple clinical and risk factor variables into an ensemble-tree based machine learning algorithm and derived models to predict the probability of developing PD. We also investigated relationships of predictive models and neuropathologic features such as nigral neuron density.Results:The study sample included 292 subjects, 25 of whom developed PD within 3 years and 41 by 5 years. 116 (46%) of 251 subjects not diagnosed with PD underwent autopsy. Light Gradient Boosting Machine modeling of 12 predictors correctly classified a high proportion of individuals who developed PD within 3 years (area under the curve (AUC) 0.82, 95%CI 0.76–0.89) or 5 years (AUC 0.77, 95%CI 0.71–0.84). A large proportion of controls who were misclassified as PD had Lewy pathology at autopsy, including 79%of those who died within 3 years. PD probability estimates correlated inversely with nigral neuron density and were strongest in autopsies conducted within 3 years of index date (r = –0.57, p < 0.01).Conclusion:Machine learning can identify persons likely to develop PD during the prodromal period using questionnaires and simple non-invasive tests. Correlation with neuropathology suggests that true model accuracy may be considerably higher than estimates based solely on clinical diagnosis.

Machine learning prediction of mortality in venous thromboembolism patients: the Birmingham Black Country Venous Thromboembolism (BBC-VTE) cohort

Abstract Introduction Venous thromboembolism (VTE), including deep vein thrombosis (DVT) and pulmonary embolism (PE), is one of the main causes of preventable death in hospitals in the UK. Current clinical risk scores to predict mortality of patients with VTE are the pulmonary embolism severity index (PESI) and the simplified PESI (sPESI) which have similar predictive power. Purpose To evaluate the ability of machine learning algorithms to predict mortality in patients admitted with VTE and to compare their predictive capability with the sPESI score for 30-day mortality. Methods The BBC-VTE was a retrospective multicentre patient cohort established to determine clinical features and novel aspects of risk prediction for VTE (and VTE-related complications) in a contemporary cohort. We include a cohort of 1554 patients (mean age 65.6 years; 53% female) who represent all consecutive admissions with a final diagnosis of VTE to one of 3 regional hospitals in the West Midlands, UK during the years 2012–2014. The dataset was split into training (70%) and validation (30%) cohorts. We trained two tree-based models, Random Forests (RF) and XGBoost (XG), using 5-fold cross-validation on the training cohort to predict patient mortality. This was validated using the held-out validation cohort and compared to a simple logistic regression model. To provide a comparison with the sPESI score, we extracted a sub-group of patients (n=652) who had values for oxygen saturation, systolic blood pressure, heart rate, history of cancer, history of cardiopulmonary disease, and age. We used RF to determine the mortality prediction using: i) only the sPESI variables listed and; ii) all the clinical variables available to us. This was then compared against the standard sPESI prediction for this cohort. C-indices (AUC) were used for comparison. Results The c-indices for RF and XG using the full patient cohort were 0.85 [95% CI: 0.80 – 0.90] (Fig. 1a) and 0.82 [95% CI: 0.77 - 0.87], with the logistic regression c-index being 0.83 [95% CI: 0.78 – 0.88]. The reported sPESI c-index was significantly smaller (p&amp;lt;0.05) than the RF c-index (0.75 [95% CI: 0.69–0.80]). The most important features for prediction of mortality indicated by the RF algorithm are age, admission blood levels, discharge oral anticoagulation, and previous malignancy (Fig. 2). The sPESI score c-index for the subgroup of patients was found to be 0.72. In comparison, using RF with the same variables gives a significantly larger (p&amp;lt;0.05) c-index of 0.78 [95% CI: 0.73 – 0.83]. When using all clinical variables available the c-index increased to 0.85 [95% CI: 0.80 – 0.90] (Fig. 1b). Conclusion Application of machine learning using simple clinical variables in hospital settings can improve prediction of mortality post-VTE event above-and-beyond the current simplified PESI risk score. Prospective study is warranted to validate the algorithm on external datasets and to construct individualised risk predictions. Funding Acknowledgement Type of funding sources: None. Figure 1. ROC curve comparisons with sPESIFigure 2. Feature Importances