Osteoporotic hip fracture prediction from risk factors available in administrative claims data – A machine learning approach

Abstract Background Early recognition and management of baseline risk factors may play an important role in reducing glaucoma surgery burdens. However, no studies have investigated them using real-world data in Japan or other countries. This study aimed to clarify the risk factors leading to trabeculectomy surgery, which is the most common procedure of glaucoma surgery, of glaucoma patient using the Japanese nationwide administrative claims data associated with the diagnosis procedure combination (DPC) system. Methods It was a retrospective, non-interventional cohort study. Data were collected from patients who were admitted to DPC participating hospitals, nationwide acute care hospitals and were diagnosed with glaucoma between 2012 to 2018. The primary outcome was the risk factors associated with trabeculectomy surgery. The association between baseline characteristics and trabeculectomy surgery was identified using multivariable logistic regression analysis by comparing patients with and without trabeculectomy surgery. Meanwhile, the secondary outcomes included the rate of comorbidities, the rate of concomitant drug use and the treatment patterns of glaucoma eye drops at the index admission. Among patients with trabeculectomy surgery, the risk factors leading to cataract surgery were also evaluated as subgroup analysis. Results A total of 29,599 patients included in the analysis, 12,038 and 17,561 patients were in the glaucoma surgery and non-glaucoma surgery cohorts, respectively. The factors associated with the increase in trabeculectomy surgery were having allergies, taking concomitant drugs including cancer, depression, ischemic heart disease and peptic ulcer, being diagnosed with primary open-angle glaucoma and longer length of stay in hospital. In contrast, the factors associated with the decrease in trabeculectomy surgery were having hypertension, taking hypertension drug, age ≥ 80 and female. Conclusions Special focus on Japanese patients with glaucoma who have allergy-related comorbidities or take immune, nervous, circulatory or gastrointestinal system-related concomitant drugs seems to be desirable.

Download Full-text

Supplementing Claims Data with Electronic Medical Records to Improve Estimation and Classification of Rheumatoid Arthritis Disease Activity: A Machine Learning Approach

ACR Open Rheumatology ◽

10.1002/acr2.11068 ◽

2019 ◽

Vol 1 (9) ◽

pp. 552-559 ◽

Cited By ~ 1

Author(s):

Candace H. Feldman ◽

Kazuki Yoshida ◽

Chang Xu ◽

Michelle L. Frits ◽

Nancy A. Shadick ◽

...

Keyword(s):

Rheumatoid Arthritis ◽

Machine Learning ◽

Electronic Medical Records ◽

Medical Records ◽

Claims Data ◽

Learning Approach ◽

Rheumatoid Arthritis Disease Activity ◽

Rheumatoid Arthritis Disease ◽

Machine Learning Approach

Download Full-text

Understanding the importance of key risk factors in predicting chronic bronchitic symptoms using a machine learning approach

BMC Medical Research Methodology ◽

10.1186/s12874-019-0708-x ◽

2019 ◽

Vol 19 (1) ◽

Cited By ~ 4

Author(s):

Huiyu Deng ◽

Robert Urman ◽

Frank D. Gilliland ◽

Sandrah P. Eckel

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Learning Approach ◽

Machine Learning Approach

Download Full-text

Predicting Congestive Heart Failure Risk Factors in King Abdulaziz Medical City A Machine Learning Approach

2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA) ◽

10.1109/caida51941.2021.9425233 ◽

2021 ◽

Author(s):

Ayidh Alqahtani ◽

Ryiad Alshmmari ◽

Mohammed Alzunitan ◽

Amjad Ahmed ◽

Abdelmajid Mukhtar ◽

...

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Heart Failure ◽

Congestive Heart Failure ◽

Learning Approach ◽

Failure Risk ◽

Machine Learning Approach ◽

Medical City

Download Full-text

Assessment of bilateral knee pain from MR imaging using deep neural networks

10.1101/463497 ◽

2018 ◽

Author(s):

Gary H. Chang ◽

David T. Felson ◽

Shangran Qiu ◽

Terence D. Capellini ◽

Vijaya B. Kolachalama

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Neural Networks ◽

Deep Learning ◽

Knee Pain ◽

Deep Neural Networks ◽

Learning Approach ◽

Mr Images ◽

Bilateral Knee ◽

Machine Learning Approach

ABSTRACTBackground and objectiveIt remains difficult to characterize pain in knee joints with osteoarthritis solely by radiographic findings. We sought to understand how advanced machine learning methods such as deep neural networks can be used to analyze raw MRI scans and predict bilateral knee pain, independent of other risk factors.MethodsWe developed a deep learning framework to associate information from MRI slices taken from the left and right knees of subjects from the Osteoarthritis Initiative with bilateral knee pain. Model training was performed by first extracting features from two-dimensional (2D) sagittal intermediate-weighted turbo spin echo slices. The extracted features from all the 2D slices were subsequently combined to directly associate using a fused deep neural network with the output of interest as a binary classification problem.ResultsThe deep learning model resulted in predicting bilateral knee pain on test data with 70.1% mean accuracy, 51.3% mean sensitivity, and 81.6% mean specificity. Systematic analysis of the predictions on the test data revealed that the model performance was consistent across subjects of different Kellgren-Lawrence grades.ConclusionThe study demonstrates a proof of principle that a machine learning approach can be applied to associate MR images with bilateral knee pain.SIGNIFICANCE AND INNOVATIONKnee pain is typically considered as an early indicator of osteoarthritis (OA) risk. Emerging evidence suggests that MRI changes are linked to pre-clinical OA, thus underscoring the need for building image-based models to predict knee pain. We leveraged a state-of-the-art machine learning approach to associate raw MR images with bilateral knee pain, independent of other risk factors.

Download Full-text

A machine learning approach to predict early outcomes after pituitary adenoma surgery

Neurosurgical FOCUS ◽

10.3171/2018.8.focus18268 ◽

2018 ◽

Vol 45 (5) ◽

pp. E8 ◽

Cited By ~ 9

Author(s):

Todd C. Hollon ◽

Adish Parikh ◽

Balaji Pandian ◽

Jamaal Tarpeh ◽

Daniel A. Orringer ◽

...

Keyword(s):

Machine Learning ◽

Risk Factors ◽

Pituitary Adenoma ◽

Predictive Model ◽

Odds Ratio ◽

Postoperative Outcomes ◽

Learning Approach ◽

Ratio Analysis ◽

Machine Learning Approach ◽

The Mean

OBJECTIVEPituitary adenomas occur in a heterogeneous patient population with diverse perioperative risk factors, endocrinopathies, and other tumor-related comorbidities. This heterogeneity makes predicting postoperative outcomes challenging when using traditional scoring systems. Modern machine learning algorithms can automatically identify the most predictive risk factors and learn complex risk-factor interactions using training data to build a robust predictive model that can generalize to new patient cohorts. The authors sought to build a predictive model using supervised machine learning to accurately predict early outcomes of pituitary adenoma surgery.METHODSA retrospective cohort of 400 consecutive pituitary adenoma patients was used. Patient variables/predictive features were limited to common patient characteristics to improve model implementation. Univariate and multivariate odds ratio analysis was performed to identify individual risk factors for common postoperative complications and to compare risk factors with model predictors. The study population was split into 300 training/validation patients and 100 testing patients to train and evaluate four machine learning models using binary classification accuracy for predicting early outcomes.RESULTSThe study included a total of 400 patients. The mean ± SD patient age was 53.9 ± 16.3 years, 59.8% of patients had nonfunctioning adenomas and 84.7% had macroadenomas, and the mean body mass index (BMI) was 32.6 ± 7.8 (58.0% obesity rate). Multivariate odds ratio analysis demonstrated that age < 40 years was associated with a 2.86 greater odds of postoperative diabetes insipidus and that nonobese patients (BMI < 30) were 2.2 times more likely to develop postoperative hyponatremia. Using broad criteria for a poor early postoperative outcome—major medical and early surgical complications, extended length of stay, emergency department admission, inpatient readmission, and death—31.0% of patients met criteria for a poor early outcome. After model training, a logistic regression model with elastic net (LR-EN) regularization best predicted early postoperative outcomes of pituitary adenoma surgery on the 100-patient testing set—sensitivity 68.0%, specificity 93.3%, overall accuracy 87.0%. The receiver operating characteristic and precision-recall curves for the LR-EN model had areas under the curve of 82.7 and 69.5, respectively. The most important predictive variables were lowest perioperative sodium, age, BMI, highest perioperative sodium, and Cushing’s disease.CONCLUSIONSEarly postoperative outcomes of pituitary adenoma surgery can be predicted with 87% accuracy using a machine learning approach. These results provide insight into how predictive modeling using machine learning can be used to improve the perioperative management of pituitary adenoma patients.

Download Full-text