scholarly journals Improving Pre-eclampsia Risk Prediction by Modeling Individualized Pregnancy Trajectories Derived from Routinely Collected Electronic Medical Record Data

2021 ◽  
Author(s):  
Shilong Li ◽  
Zichen Wang ◽  
Luciana A. Vieira ◽  
Amanda B. Zheutlin ◽  
Boshu Ru ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
At Risk ◽  
Complete Blood Count ◽  
Early Recognition ◽  
Training Dataset ◽  
Validation Dataset ◽  
Time Period ◽  
Patients At Risk ◽  
Mount Sinai

ABSTRACTPreeclampsia (PE) is a heterogeneous and complex disease associated with rising morbidity and mortality in pregnant women and newborns in the US. Early recognition of patients at risk is a pressing clinical need to significantly reduce the risk of adverse pregnancy outcomes. We assessed whether information routinely collected and stored on women in their electronic medical records (EMR) could enhance the prediction of PE risk beyond what is achieved in standard of care assessments today. We developed a digital phenotyping algorithm to assemble and curate 108,557 pregnancies from EMRs across the Mount Sinai Health System (MSHS), accurately reconstructing pregnancy journeys and normalizing these journeys across different hospital EMR systems. We then applied machine learning approaches to a training dataset from Mount Sinai Hospital (MSH) (N = 60,879) to construct predictive models of PE across three major pregnancy time periods (ante-, intra-, and postpartum). The resulting models predicted PE with high accuracy across the different pregnancy periods, with areas under the receiver operating characteristic curves (AUC) of 0.92, 0.83 and 0.89 at 37 gestational weeks, intrapartum and postpartum, respectively. We observed comparable performance in two independent patient cohorts with diverse patient populations (MSH validation dataset N = 38,421 and Mount Sinai West dataset N = 9,257). While our machine learning approach identified known risk factors of PE (such as blood pressure, weight and maternal age), it also identified novel PE risk factors, such as complete blood count related characteristics for the antepartum time period and ibuprofen usage for the postpartum time period. Our model not only has utility for earlier identification of patients at risk for PE, but given the prediction accuracy substantially exceeds what is achieved today in clinical practice, our model provides a path for promoting personalized precision therapeutic strategies for patients at risk.

scholarly journals Using Predictive Modeling and Supervised Machine Learning to Identify Patients at Risk for Venous Thromboembolism Following Posterior Lumbar Fusion

2021 ◽  
pp. 219256822110193
Author(s):  
Kevin Y. Wang ◽  
Ijezie Ikwuezunma ◽  
Varun Puvanesarajah ◽  
Jacob Babu ◽  
Adam Margalit ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Venous Thromboembolism ◽  
Risk Stratification ◽  
Predictive Model ◽  
Predictive Modeling ◽  
Lumbar Fusion ◽  
Posterior Lumbar Fusion ◽  
Single Level ◽  
Patients At Risk

Study Design: Retrospective review. Objective: To use predictive modeling and machine learning to identify patients at risk for venous thromboembolism (VTE) following posterior lumbar fusion (PLF) for degenerative spinal pathology. Methods: Patients undergoing single-level PLF in the inpatient setting were identified in the National Surgical Quality Improvement Program database. Our outcome measure of VTE included all patients who experienced a pulmonary embolism and/or deep venous thrombosis within 30-days of surgery. Two different methodologies were used to identify VTE risk: 1) a novel predictive model derived from multivariable logistic regression of significant risk factors, and 2) a tree-based extreme gradient boosting (XGBoost) algorithm using preoperative variables. The methods were compared against legacy risk-stratification measures: ASA and Charlson Comorbidity Index (CCI) using area-under-the-curve (AUC) statistic. Results: 13, 500 patients who underwent single-level PLF met the study criteria. Of these, 0.95% had a VTE within 30-days of surgery. The 5 clinical variables found to be significant in the multivariable predictive model were: age > 65, obesity grade II or above, coronary artery disease, functional status, and prolonged operative time. The predictive model exhibited an AUC of 0.716, which was significantly higher than the AUCs of ASA and CCI (all, P < 0.001), and comparable to that of the XGBoost algorithm ( P > 0.05). Conclusion: Predictive analytics and machine learning can be leveraged to aid in identification of patients at risk of VTE following PLF. Surgeons and perioperative teams may find these tools useful to augment clinical decision making risk stratification tool.

scholarly journals KDClassifier: Urinary Proteomic Spectra Analysis Based on Machine Learning for Classification of Kidney Diseases

2020 ◽  
Author(s):  
Wanjun Zhao ◽  
Yong Zhang ◽  
Xinming Li ◽  
Yonghong Mao ◽  
Changwei Wu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mass Spectrum ◽  
Kidney Disease ◽  
Kidney Diseases ◽  
Training Dataset ◽  
Validation Dataset ◽  
Support Vector ◽  
Urinary Proteomics ◽  
Diagnosis Model

AbstractBackgroundBy extracting the spectrum features from urinary proteomics based on an advanced mass spectrometer and machine learning algorithms, more accurate reporting results can be achieved for disease classification. We attempted to establish a novel diagnosis model of kidney diseases by combining machine learning with an extreme gradient boosting (XGBoost) algorithm with complete mass spectrum information from the urinary proteomics.MethodsWe enrolled 134 patients (including those with IgA nephropathy, membranous nephropathy, and diabetic kidney disease) and 68 healthy participants as a control, and for training and validation of the diagnostic model, applied a total of 610,102 mass spectra from their urinary proteomics produced using high-resolution mass spectrometry. We divided the mass spectrum data into a training dataset (80%) and a validation dataset (20%). The training dataset was directly used to create a diagnosis model using XGBoost, random forest (RF), a support vector machine (SVM), and artificial neural networks (ANNs). The diagnostic accuracy was evaluated using a confusion matrix. We also constructed the receiver operating-characteristic, Lorenz, and gain curves to evaluate the diagnosis model.ResultsCompared with RF, the SVM, and ANNs, the modified XGBoost model, called a Kidney Disease Classifier (KDClassifier), showed the best performance. The accuracy of the diagnostic XGBoost model was 96.03% (CI = 95.17%-96.77%; Kapa = 0.943; McNemar’s Test, P value = 0.00027). The area under the curve of the XGBoost model was 0.952 (CI = 0.9307-0.9733). The Kolmogorov-Smirnov (KS) value of the Lorenz curve was 0.8514. The Lorenz and gain curves showed the strong robustness of the developed model.ConclusionsThis study presents the first XGBoost diagnosis model, i.e., the KDClassifier, combined with complete mass spectrum information from the urinary proteomics for distinguishing different kidney diseases. KDClassifier achieves a high accuracy and robustness, providing a potential tool for the classification of all types of kidney diseases.

scholarly journals Identifying those at risk of reattendance at discharge from emergency departments using explainable machine learning

2020 ◽  
Author(s):  
F. P. Chmiel ◽  
M. Azor ◽  
F. Borca ◽  
M. J. Boniface ◽  
D. K. Burns ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Emergency Departments ◽  
Risk Groups ◽  
Machine Learning Algorithms ◽  
Care Indicator ◽  
Number Of Patients ◽  
Increased Risk ◽  
Single Centre Study ◽  
Patients At Risk

ABSTRACTShort-term reattendances to emergency departments are a key quality of care indicator. Identifying patients at increased risk of early reattendance can help reduce the number of patients with missed or undertreated illness or injury, and could support appropriate discharges with focused interventions. In this manuscript we present a retrospective, single-centre study where we create and evaluate a machine-learnt classifier trained to identify patients at risk of reattendance within 72 hours of discharge from an emergency department. On a patient hold-out test set, our highest performing classifier obtained an AUROC of 0.748 and an average precision of 0.250; demonstrating that machine-learning algorithms can be used to classify patients, with moderate performance, into low and high-risk groups for reattendance. In parallel to our predictive model we train an explanation model, capable of explaining predictions at an attendance level, which can be used to help inform the design of interventional strategies.

scholarly journals Discovery of Highly Polymorphic Organic Materials: A New Machine Learning Approach

2019 ◽  
Author(s):  
Zied Hosni ◽  
Annalisa Riccardi ◽  
Stephanie Yerdelen ◽  
Alan R. G. Martin ◽  
Deborah Bowering ◽  
...  
Keyword(s):  
Machine Learning ◽  
Structure Prediction ◽  
External Validation ◽  
New Drugs ◽  
Training Dataset ◽  
Validation Dataset ◽  
Machine Learning Classification ◽  
Novel Approach ◽  
Physical Form ◽  
Machine Learning Approach

<div><div><p>Polymorphism is the capacity of a molecule to adopt different conformations or molecular packing arrangements in the solid state. This is a key property to control during pharmaceutical manufacturing because it can impact a range of properties including stability and solubility. In this study, a novel approach based on machine learning classification methods is used to predict the likelihood for an organic compound to crystallise in multiple forms. A training dataset of drug-like molecules was curated from the Cambridge Structural Database (CSD) and filtered according to entries in the Drug Bank database. The number of separate forms in the CSD for each molecule was recorded. A metaclassifier was trained using this dataset to predict the expected number of crystalline forms from the compound descriptors. This approach was used to estimate the number of crystallographic forms for an external validation dataset. These results suggest this novel methodology can be used to predict the extent of polymorphism of new drugs or not-yet experimentally screened molecules. This promising method complements expensive ab initio methods for crystal structure prediction and as integral to experimental physical form screening, may identify systems that with unexplored potential.</p> </div> </div>

SCREENING OF PATIENTS AT RISK FOR WILD TYPE ATTR-CM USING A COMPUTATIONAL MACHINE LEARNING ALGORITHM

2021 ◽  
Vol 37 (10) ◽  
pp. S65
Author(s):  
C Willis ◽  
K Kawamoto ◽  
A Watanabe ◽  
J Biskupiak ◽  
K Nolen ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Wild Type ◽  
Patients At Risk

scholarly journals MEWS++: Enhancing the Prediction of Clinical Deterioration in Admitted Patients through a Machine Learning Model

2020 ◽  
Vol 9 (2) ◽  
pp. 343 ◽  
Author(s):  
Arash Kia ◽  
Prem Timsina ◽  
Himanshu N. Joshi ◽  
Eyal Klang ◽  
Rohit R. Gupta ◽  
...  
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Area Under The Curve ◽  
Learning Model ◽  
Clinical Deterioration ◽  
Early Warning Score ◽  
Support Vector ◽  
Adult Age ◽  
Machine Learning Model ◽  
Patients At Risk

Early detection of patients at risk for clinical deterioration is crucial for timely intervention. Traditional detection systems rely on a limited set of variables and are unable to predict the time of decline. We describe a machine learning model called MEWS++ that enables the identification of patients at risk of escalation of care or death six hours prior to the event. A retrospective single-center cohort study was conducted from July 2011 to July 2017 of adult (age > 18) inpatients excluding psychiatric, parturient, and hospice patients. Three machine learning models were trained and tested: random forest (RF), linear support vector machine, and logistic regression. We compared the models’ performance to the traditional Modified Early Warning Score (MEWS) using sensitivity, specificity, and Area Under the Curve for Receiver Operating Characteristic (AUC-ROC) and Precision-Recall curves (AUC-PR). The primary outcome was escalation of care from a floor bed to an intensive care or step-down unit, or death, within 6 h. A total of 96,645 patients with 157,984 hospital encounters and 244,343 bed movements were included. Overall rate of escalation or death was 3.4%. The RF model had the best performance with sensitivity 81.6%, specificity 75.5%, AUC-ROC of 0.85, and AUC-PR of 0.37. Compared to traditional MEWS, sensitivity increased 37%, specificity increased 11%, and AUC-ROC increased 14%. This study found that using machine learning and readily available clinical data, clinical deterioration or death can be predicted 6 h prior to the event. The model we developed can warn of patient deterioration hours before the event, thus helping make timely clinical decisions.

Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis

2019 ◽  
Vol 73 (4) ◽  
pp. 334-344 ◽  
Author(s):  
Ryan J. Delahanty ◽  
JoAnn Alvarez ◽  
Lisa M. Flynn ◽  
Robert L. Sherwin ◽  
Spencer S. Jones
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Early Identification ◽  
Learning Model ◽  
Machine Learning Model ◽  
Patients At Risk

scholarly journals Predicting Persistent Opioid Use, Abuse, and Toxicity Among Cancer Survivors

2019 ◽  
Vol 112 (7) ◽  
pp. 720-727 ◽  
Author(s):  
Lucas K Vitzthum ◽  
Paul Riviere ◽  
Paige Sheridan ◽  
Vinit Nalawade ◽  
Rishi Deka ◽  
...  
Keyword(s):  
Risk Factors ◽  
At Risk ◽  
Cancer Survivors ◽  
Critical Role ◽  
Multivariable Analysis ◽  
Area Under The Curve ◽  
Opioid Abuse ◽  
Opioid Use ◽  
Multivariable Logistic Regression Model ◽  
Patients At Risk

Abstract Background Although opioids play a critical role in the management of cancer pain, the ongoing opioid epidemic has raised concerns regarding their persistent use and abuse. We lack data-driven tools in oncology to understand the risk of adverse opioid-related outcomes. This project seeks to identify clinical risk factors and create a risk score to help identify patients at risk of persistent opioid use and abuse. Methods Within a cohort of 106 732 military veteran cancer survivors diagnosed between 2000 and 2015, we determined rates of persistent posttreatment opioid use, diagnoses of opioid abuse or dependence, and admissions for opioid toxicity. A multivariable logistic regression model was used to identify patient, cancer, and treatment risk factors associated with adverse opioid-related outcomes. Predictive risk models were developed and validated using a least absolute shrinkage and selection operator regression technique. Results The rate of persistent opioid use in cancer survivors was 8.3% (95% CI = 8.1% to 8.4%); the rate of opioid abuse or dependence was 2.9% (95% CI = 2.8% to 3.0%); and the rate of opioid-related admissions was 2.1% (95% CI = 2.0% to 2.2%). On multivariable analysis, several patient, demographic, and cancer and treatment factors were associated with risk of persistent opioid use. Predictive models showed a high level of discrimination when identifying individuals at risk of adverse opioid-related outcomes including persistent opioid use (area under the curve [AUC] = 0.85), future diagnoses of opioid abuse or dependence (AUC = 0.87), and admission for opioid abuse or toxicity (AUC = 0.78). Conclusion This study demonstrates the potential to predict adverse opioid-related outcomes among cancer survivors. With further validation, personalized risk-stratification approaches could guide management when prescribing opioids in cancer patients.

scholarly journals Mathematical modelling of FEV1% allows early recognition of patients at risk

2009 ◽  
Vol 8 ◽  
pp. S58
Author(s):  
F. Gatti ◽  
A. Pugliese ◽  
P. Iansa ◽  
B.M. Assael
Keyword(s):  
At Risk ◽  
Mathematical Modelling ◽  
Early Recognition ◽  
Patients At Risk

scholarly journals A real-world demonstration of machine learning generalizability in the detection of intracranial hemorrhage on head computerized tomography

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Hojjat Salehinejad ◽  
Jumpei Kitamura ◽  
Noah Ditkofsky ◽  
Amy Lin ◽  
Aditya Bharatha ◽  
...  
Keyword(s):  
Machine Learning ◽  
Medical Imaging ◽  
Intracranial Hemorrhage ◽  
Real World ◽  
External Validation ◽  
Model Performance ◽  
Training Dataset ◽  
Validation Dataset ◽  
Great Promise ◽  
Clinical Environments

AbstractMachine learning (ML) holds great promise in transforming healthcare. While published studies have shown the utility of ML models in interpreting medical imaging examinations, these are often evaluated under laboratory settings. The importance of real world evaluation is best illustrated by case studies that have documented successes and failures in the translation of these models into clinical environments. A key prerequisite for the clinical adoption of these technologies is demonstrating generalizable ML model performance under real world circumstances. The purpose of this study was to demonstrate that ML model generalizability is achievable in medical imaging with the detection of intracranial hemorrhage (ICH) on non-contrast computed tomography (CT) scans serving as the use case. An ML model was trained using 21,784 scans from the RSNA Intracranial Hemorrhage CT dataset while generalizability was evaluated using an external validation dataset obtained from our busy trauma and neurosurgical center. This real world external validation dataset consisted of every unenhanced head CT scan (n = 5965) performed in our emergency department in 2019 without exclusion. The model demonstrated an AUC of 98.4%, sensitivity of 98.8%, and specificity of 98.0%, on the test dataset. On external validation, the model demonstrated an AUC of 95.4%, sensitivity of 91.3%, and specificity of 94.1%. Evaluating the ML model using a real world external validation dataset that is temporally and geographically distinct from the training dataset indicates that ML generalizability is achievable in medical imaging applications.

Sign in / Sign up

Export Citation Format

Share Document