Multiscale modelling of Potts shunt as a potential palliative treatment for suprasystemic idiopathic pulmonary artery hypertension: a paediatric case study

Potts shunt (PS) was suggested as palliation for patients with suprasystemic pulmonary arterial hypertension (PAH) and right ventricular (RV) failure. PS, however, can result in poorly understood mortality. Here, a patient-specific geometrical multiscale model of PAH physiology and PS is developed for a paediatric PAH patient with stent-based PS. In the model, 7.6mm-diameter PS produces near-equalisation of the aortic and PA pressures and $$Q_p/Q_s$$ Q p / Q s (oxygenated vs deoxygenated blood flow) ratio of 0.72 associated with a 16% decrease of left ventricular (LV) output and 18% increase of RV output. The flow from LV to aortic arch branches increases by 16%, while LV contribution to the lower body flow decreases by 29%. Total flow in the descending aorta (DAo) increases by 18% due to RV contribution through the PS with flow into the distal PA branches decreasing. PS induces 18% increase of RV work due to its larger stroke volume pumped against lower afterload. Nonetheless, larger RV work does not lead to increased RV end-diastolic volume. Three-dimensional flow assessment demonstrates the PS jet impinging with a high velocity and wall shear stress on the opposite DAo wall with the most of the shunt flow being diverted to the DAo. Increasing the PS diameter from 5mm up to 10mm results in a nearly linear increase in post-operative shunt flow and a nearly linear decrease in shunt pressure-drop. In conclusion, this model reasonably represents patient-specific haemodynamics pre- and post-creation of the PS, providing insights into physiology of this complex condition, and presents a predictive tool that could be useful for clinical decision-making regarding suitability for PS in PAH patients with drug-resistant suprasystemic PAH.

Reducing Waiting Time in the General Pediatric Clinic at Al Wakra Hospital, Qatar

Background: Waiting times for clinic appointments constitute a key indicator of an outpatient department performance for access to care and patient satisfaction. This is particularly relevant for pediatric population. The Ministry of Public Health in Qatar set a waiting time of 28 days for patients to get new appointment in General Outpatient Department (GOPD). The current average waiting time to get a new appointment in the general pediatric clinic (GPC) at AWH is 57 days. Aim: Decrease the average waiting time to get a new clinic appointment from 57 days to 28 days by the end of December 2018, and to meet the national targets set by the Ministry of Public Health. Methodology: This is a Quality Improvement (QI) project using the Model for Improvement (MFI). The MFI framework is designed to support organizations answering fundamental questions before agreeing on drivers for change. The implementation of change was be facilitated by the Plan-Do-Study-Act (PDSA) cycles methodology. The QI project team performed a root cause analysis using the Ishikawa diagram and identified the key contributing factors to the long waiting times to get a new appointment. Twenty-seven PDSA cycle ramps were designed with support of predictive tool to test innovative changes in current operational processes in an attempt to improve waiting time in the general pediatric clinic at Al Wakra Hospital. Results: The monthly average number of referrals for GPC increased by 200% between the pre and post implementation periods. The average triage waiting time improved from 6 to 2.6 days in 2018 and the average become 1 day in 2019. Post-implementation the average waiting time for patients to get new appointment improved from 57 days to 28 days in 2018 and the average waiting time improved to 16 days in 2019. Conclusion: The quality improvement project for the AWH general pediatric clinic demonstrates significant improvement in waiting times for new appointments, the recommendation for the hospital leadership would be to rollout the improvement methodology to other clinics that suffer from similar challenges.

A predictive model for postoperative progressive haemorrhagic injury in traumatic brain injuries

Background Progressive haemorrhagic injury after surgery in patients with traumatic brain injury often results in poor patient outcomes. This study aimed to develop and validate a practical predictive tool that can reliably estimate the risk of postoperative progressive haemorrhagic injury (PHI) in patients with traumatic brain injury (TBI). Methods Data from 645 patients who underwent surgery for TBI between March 2018 and December 2020 were collected. The outcome was postoperative intracranial PHI, which was assessed on postoperative computed tomography. The least absolute shrinkage and selection operator (LASSO) regression model, univariate analysis, and Delphi method were applied to select the most relevant prognostic predictors. We combined conventional coagulation test (CCT) data, thromboelastography (TEG) variables, and several predictors to develop a predictive model using binary logistic regression and then presented the results as a nomogram. The predictive performance of the model was assessed with calibration and discrimination. Internal validation was assessed. Results The signature, which consisted of 11 selected features, was significantly associated with intracranial PHI (p < 0.05, for both primary and validation cohorts). Predictors in the prediction nomogram included age, S-pressure, D-pressure, pulse, temperature, reaction time, PLT, prothrombin time, activated partial thromboplastin time, FIB, and kinetics values. The model showed good discrimination, with an area under the curve of 0.8694 (95% CI, 0.8083–0.9304), and good calibration. Conclusion This model is based on a nomogram incorporating CCT and TEG variables, which can be conveniently derived at hospital admission. It allows determination of this individual risk for postoperative intracranial PHI and will facilitate a timely intervention to improve outcomes.

Using Innovative Machine Learning Methods to Screen and Identify Predictors of Congenital Heart Diseases

Objective: Congenital heart diseases (CHDs) are associated with an extremely heavy global disease burden as the most common category of birth defects. Genetic and environmental factors have been identified as risk factors of CHDs previously. However, high volume clinical indicators have never been considered when predicting CHDs. This study aimed to predict the occurrence of CHDs by considering thousands of variables from self-reported questionnaires and routinely collected clinical laboratory data using machine learning algorithms.Methods: We conducted a birth cohort study at one of the largest cardiac centers in China from 2011 to 2017. All fetuses were screened for CHDs using ultrasound and cases were confirmed by at least two pediatric cardiologists using echocardiogram. A total of 1,127 potential predictors were included to predict CHDs. We used the Explainable Boosting Machine (EBM) for prediction and evaluated the model performance using area under the Receive Operating Characteristics (ROC) curves (AUC). The top predictors were selected according to their contributions and predictive values. Thresholds were calculated for the most significant predictors.Results: Overall, 5,390 mother-child pairs were recruited. Our prediction model achieved an AUC of 76% (69-83%) from out-of-sample predictions. Among the top 35 predictors of CHDs we identified, 34 were from clinical laboratory tests and only one was from the questionnaire (abortion history). Total accuracy, sensitivity, and specificity were 0.65, 0.74, and 0.65, respectively. Maternal serum uric acid (UA), glucose, and coagulation levels were the most consistent and significant predictors of CHDs. According to the thresholds of the predictors identified in our study, which did not reach the current clinical diagnosis criteria, elevated UA (&gt;4.38 mg/dl), shortened activated partial thromboplastin time (&lt;33.33 s), and elevated glucose levels were the most important predictors and were associated with ranges of 1.17-1.54 relative risks of CHDs. We have developed an online predictive tool for CHDs based on our findings that may help screening and prevention of CHDs.Conclusions: Maternal UA, glucose, and coagulation levels were the most consistent and significant predictors of CHDs. Thresholds below the current clinical definition of “abnormal” for these predictors could be used to help develop CHD screening and prevention strategies.

Invasive Prediction of Ground Glass Nodule Based on Clinical Characteristics and Radiomics Feature

Objective: To explore the diagnostic value of CT radiographic images and radiomics features for invasive classification of lung adenocarcinoma manifesting as ground-glass nodules (GGNs) in computer tomography (CT).Methods: A total of 312 GGNs were enrolled in this retrospective study. All GGNs were randomly divided into training set (n = 219) and test set (n = 93). Univariate and multivariate logistic regressions were used to establish a clinical model, while the minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) algorithm were used to select the radiomics features and construct the radiomics model. A combined model was finally built by combining these two models. The performance of these models was assessed in both training and test set. A combined nomogram was developed based on the combined model and evaluated with its calibration curves and C-index.Results: Diameter [odds ratio (OR), 1.159; p ＜ 0.001], lobulation (OR, 2.953; p = 0.002), and vascular changes (OR, 3.431; p ＜ 0.001) were retained as independent predictors of the invasive adenocarcinoma (IAC) group. Eleven radiomics features were selected by mRMR and LASSO method to established radiomics model. The clinical model and radiomics mode showed good predictive ability in both training set and test set. When two models were combined, the diagnostic area under the curve (AUC) value was higher than the single clinical or radiomics model (training set: 0.86 vs. 0.83 vs. 0.82; test set: 0.80 vs. 0.78 vs. 0.79). The constructed combined nomogram could effectively quantify the risk degree of 3 image features and Rad score with a C-index of 0.855 (95%: 0.805∼0.905).Conclusion: Radiographic and radiomics features show high accuracy in the invasive diagnosis of GGNs, and their combined analysis can improve the diagnostic efficacy of IAC manifesting as GGNs. The nomogram, serving as a noninvasive and accurate predictive tool, can help judge the invasiveness of GGNs prior to surgery and assist clinicians in creating personalized treatment strategies.

Role of portal color Doppler ultrasonography as noninvasive predictive tool for esophageal varices in cirrhotic patients

Background Esophageal varices (EV) is the most common apprehensive complication of portal hypertension in patients with cirrhotic liver. Guidelines recommend Upper gastro-intestinal endoscopic screening for EV in patients with newly diagnosed chronic cirrhosis (Imperiale et al. in Hepatology 45(4):870–878, 2007). Yet, it is invasive, time consuming and costly. To avoid unnecessary endoscopy, some studies have suggested Doppler ultrasound examination as simple, and noninvasive tool in prediction and assessment of severity of EV (Agha et al. in Dig Dis Sci 54(3):654–660, 2009). Our study was to assess the role of different Doppler indices of portal vein, hepatic and splenic arteries as a noninvasive tool for prediction of esophageal varices in cirrhotic patients. Results This prospective case control study was conducted on 100 cirrhotic liver patients and 100 of healthy volunteers as control group. Patients were subjected to clinical examination, upper gastrointestinal tract endoscopy, abdominal ultrasonography with duplex Doppler evaluation of different portal Doppler hemodynamic indices were done for each patient. The results revealed that portal vein diameter, hepatic artery pulsatility index, portal hypertensive index, portal vein flow velocity, portal congestion index have high sensitivity for prediction of EV. However, Splenic artery resistance index, hepatic artery resistance index HARI, liver vascular index and platelet count/spleen diameter have less sensitivity for prediction of EV. Conclusion Measuring the portal hemodynamic indices can help physicians as noninvasive predictors of EV in cirrhotic patients to restrict the need for unnecessary endoscopic screening especially when endoscopic facilities are limited.

Comparing machine learning algorithms for predicting COVID-19 mortality

Background The coronavirus disease (COVID-19) hospitalized patients are always at risk of death. Machine learning (ML) algorithms can be used as a potential solution for predicting mortality in COVID-19 hospitalized patients. So, our study aimed to compare several ML algorithms to predict the COVID-19 mortality using the patient’s data at the first time of admission and choose the best performing algorithm as a predictive tool for decision-making. Methods In this study, after feature selection, based on the confirmed predictors, information about 1500 eligible patients (1386 survivors and 144 deaths) obtained from the registry of Ayatollah Taleghani Hospital, Abadan city, Iran, was extracted. Afterwards, several ML algorithms were trained to predict COVID-19 mortality. Finally, to assess the models’ performance, the metrics derived from the confusion matrix were calculated. Results The study participants were 1500 patients; the number of men was found to be higher than that of women (836 vs. 664) and the median age was 57.25 years old (interquartile 18–100). After performing the feature selection, out of 38 features, dyspnea, ICU admission, and oxygen therapy were found as the top three predictors. Smoking, alanine aminotransferase, and platelet count were found to be the three lowest predictors of COVID-19 mortality. Experimental results demonstrated that random forest (RF) had better performance than other ML algorithms with accuracy, sensitivity, precision, specificity, and receiver operating characteristic (ROC) of 95.03%, 90.70%, 94.23%, 95.10%, and 99.02%, respectively. Conclusion It was found that ML enables a reasonable level of accuracy in predicting the COVID-19 mortality. Therefore, ML-based predictive models, particularly the RF algorithm, potentially facilitate identifying the patients who are at high risk of mortality and inform proper interventions by the clinicians.

HSP110 as a Diagnostic but Not a Prognostic Biomarker in Colorectal Cancer With Microsatellite Instability

Determination of microsatellite instability (MSI) using molecular test and deficient mismatch repair (dMMR) using immunohistochemistry (IHC) has major implications on colorectal cancer (CRC) management. The HSP110 T17 microsatellite has been reported to be more monomorphic than the common markers used for MSI determination. Large deletion of HSP110 T17 has been associated with efficacy of adjuvant chemotherapy in dMMR/MSI CRCs. The aim of this study was to evaluate the interest of HSP110 deletion/expression as a diagnostic tool of dMMR/MSI CRCs and a predictive tool of adjuvant chemotherapy efficacy. All patients with MSI CRC classified by molecular testing were included in this multicenter prospective cohort (n = 381). IHC of the 4 MMR proteins was carried out. HSP110 expression was carried out by IHC (n = 343), and the size of HSP110 T17 deletion was determined by PCR (n = 327). In the 293 MSI CRCs with both tests, a strong correlation was found between the expression of HSP110 protein and the size of HSP110 T17 deletion. Only 5.8% of MSI CRCs had no HSP110 T17 deletion (n = 19/327). HSP110 T17 deletion helped to re-classify 4 of the 9 pMMR/MSI discordance cases as pMMR/MSS cases. We did not observe any correlation between HSP110 expression or HSP110 T17 deletion size with time to recurrence in patients with stage II and III CRC, treated with or without adjuvant chemotherapy. HSP110 is neither a robust prognosis marker nor a predictor tool of adjuvant chemotherapy efficacy in dMMR/MSI CRC. However, HSP110 T17 is an interesting marker, which may be combined with the other pentaplex markers to identify discordant cases between MMR IHC and MSI.