Latent-Based Imputation of Laboratory Measures from Electronic Health Records: Case for Complex Diseases

Abedi, Vida; Shivakumar, Manu; Lu, Ping; Hontecillas, Raquel; Leber, Andrew; Ahuja, Mini Singh; Ulloa, Alvaro; Shellenberger, Matthew; Bassaganya‐Riera, Josep

doi:10.1101/275743

Cited by 6 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We are expanding the GNSIS dataset by incorporating a larger number of laboratory-based features; unstructured data from clinical notes such as signs and symptoms during the initial phases of patient evaluation; information about stroke subtypes; and genetic information from a subset of patients enrolled in the MyCode initiative [ 34 ]. We are also expanding our modeling strategies by (1) improving the imputation for laboratory values for EHR-mining [ 35 , 36 ], which could improve patient representation and reduce algorithmic bias; (2) applying natural language processing to expand the feature set from clinical notes; (3) developing polygenic risk score [ 37 ] using genetic information from a subset of our GNSIS cohort; (4) improving model parameter optimization using sensitivity analysis (SA)-based approaches [ 38 , 39 , 40 , 41 ]; and (5) expanding the study by incorporating more advanced methodologies, including deep learning models to compare with binary classification developed in this study. Finally, we are planning on developing models that account for the competing risk of death and other major vascular events in addition to ischemic stroke.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Long-Term Stroke Recurrence Using Machine Learning Models

Abedi

Avula

Chaudhary

et al. 2021

JCM

View full text Add to dashboard Cite

Background: The long-term risk of recurrent ischemic stroke, estimated to be between 17% and 30%, cannot be reliably assessed at an individual level. Our goal was to study whether machine-learning can be trained to predict stroke recurrence and identify key clinical variables and assess whether performance metrics can be optimized. Methods: We used patient-level data from electronic health records, six interpretable algorithms (Logistic Regression, Extreme Gradient Boosting, Gradient Boosting Machine, Random Forest, Support Vector Machine, Decision Tree), four feature selection strategies, five prediction windows, and two sampling strategies to develop 288 models for up to 5-year stroke recurrence prediction. We further identified important clinical features and different optimization strategies. Results: We included 2091 ischemic stroke patients. Model area under the receiver operating characteristic (AUROC) curve was stable for prediction windows of 1, 2, 3, 4, and 5 years, with the highest score for the 1-year (0.79) and the lowest score for the 5-year prediction window (0.69). A total of 21 (7%) models reached an AUROC above 0.73 while 110 (38%) models reached an AUROC greater than 0.7. Among the 53 features analyzed, age, body mass index, and laboratory-based features (such as high-density lipoprotein, hemoglobin A1c, and creatinine) had the highest overall importance scores. The balance between specificity and sensitivity improved through sampling strategies. Conclusion: All of the selected six algorithms could be trained to predict the long-term stroke recurrence and laboratory-based variables were highly associated with stroke recurrence. The latter could be targeted for personalized interventions. Model performance metrics could be optimized, and models can be implemented in the same healthcare system as intelligent decision support for targeted intervention.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of Long-Term Stroke Recurrence Using Machine Learning Models

Abedi

Avula

Chaudhary

et al. 2021

JCM

View full text Add to dashboard Cite

show abstract

“…The encoding matrix was then used to create different levels of data abstraction by retaining only 100 or 1000 of the encoding using the dimensionality reduction technique (Equation (3)) for each dataset. We used these predefined cut-off values based on our preliminary assessment [ 19 ], as well as empirical studies [ 20 , 21 ]. For comparison, the full rank was also used in the modeling.…”

Section: Methodsmentioning

confidence: 99%

Increasing the Density of Laboratory Measures for Machine Learning Applications

Abedi

Shivakumar

et al. 2020

JCM

View full text Add to dashboard Cite

Background. The imputation of missingness is a key step in Electronic Health Records (EHR) mining, as it can significantly affect the conclusions derived from the downstream analysis in translational medicine. The missingness of laboratory values in EHR is not at random, yet imputation techniques tend to disregard this key distinction. Consequently, the development of an adaptive imputation strategy designed specifically for EHR is an important step in improving the data imbalance and enhancing the predictive power of modeling tools for healthcare applications. Method. We analyzed the laboratory measures derived from Geisinger’s EHR on patients in three distinct cohorts—patients tested for Clostridioides difficile (Cdiff) infection, patients with a diagnosis of inflammatory bowel disease (IBD), and patients with a diagnosis of hip or knee osteoarthritis (OA). We extracted Logical Observation Identifiers Names and Codes (LOINC) from which we excluded those with 75% or more missingness. The comorbidities, primary or secondary diagnosis, as well as active problem lists, were also extracted. The adaptive imputation strategy was designed based on a hybrid approach. The comorbidity patterns of patients were transformed into latent patterns and then clustered. Imputation was performed on a cluster of patients for each cohort independently to show the generalizability of the method. The results were compared with imputation applied to the complete dataset without incorporating the information from comorbidity patterns. Results. We analyzed a total of 67,445 patients (11,230 IBD patients, 10,000 OA patients, and 46,215 patients tested for C. difficile infection). We extracted 495 LOINC and 11,230 diagnosis codes for the IBD cohort, 8160 diagnosis codes for the Cdiff cohort, and 2042 diagnosis codes for the OA cohort based on the primary/secondary diagnosis and active problem list in the EHR. Overall, the most improvement from this strategy was observed when the laboratory measures had a higher level of missingness. The best root mean square error (RMSE) difference for each dataset was recorded as −35.5 for the Cdiff, −8.3 for the IBD, and −11.3 for the OA dataset. Conclusions. An adaptive imputation strategy designed specifically for EHR that uses complementary information from the clinical profile of the patient can be used to improve the imputation of missing laboratory values, especially when laboratory codes with high levels of missingness are included in the analysis.

show abstract

“…67,68 Imputation, predicting missing values, also has its unique challenges. Standardized techniques such as the MICE algorithm 69 or novel imputation methods 70 have been proposed. Other challenges in mining the EHR data includes: 1) different protocols and changes are introduced at various time period, without documentation for the research team; and 2) policy changes and reimbursement rules are introduced that may affect how patients seek care and how the treatment is re-designed based on their needs and their insurance coverage.…”

Section: Challenges and Perspectivesmentioning

confidence: 99%

Artificial Intelligence Transforms the Future of Health Care

Noorbakhsh-Sabet

Zand

Zhang

et al. 2019

The American Journal of Medicine

373

178

View full text Add to dashboard Cite

Life sciences researchers using Artificial Intelligence are under pressure to innovate faster than ever. Large, multilevel, and integrated datasets offer the promise of unlocking novel insights and accelerating breakthroughs. Although more data are available than ever, only a fraction is being curated, integrated, understood, and analyzed. Artificial Intelligence focuses on how computers learn from data and mimic human thought processes. Artificial Intelligence increases learning capacity and provides decision support system at scales that are transforming the future of healthcare. This article is a review of machine learning applications in healthcare with a focus on clinical, translational, and public health applications with an overview of the important role of privacy, data-sharing, and genetic information.

show abstract

Latent-Based Imputation of Laboratory Measures from Electronic Health Records: Case for Complex Diseases

Cited by 6 publications

References 13 publications

Prediction of Long-Term Stroke Recurrence Using Machine Learning Models

Prediction of Long-Term Stroke Recurrence Using Machine Learning Models

Increasing the Density of Laboratory Measures for Machine Learning Applications

Artificial Intelligence Transforms the Future of Health Care

Contact Info

Product

Resources

About