Search Articles

Development and External Validation of a Machine Learning Tool to Rule Out COVID-19 Among Adults in the Emergency Department Using Routine Blood Tests: A Large, Multicenter, Real-World Study

For the sensitivity data set: COVID-19 positivity included the same 952 PCR-positives from the 21 hospitals in the external validation data set.

Timothy B Plante, Aaron M Blau, Adrian N Berg, Aaron S Weinberg, Ik C Jun, Victor F Tapson, Tanya S Kanigan, Artur B Adib

J Med Internet Res 2020;22(12):e24048

Download Citation: END BibTex RIS

External Validation Study of First Trimester Obstetric Prediction Models (Expect Study I): Research Protocol and Population Characteristics

validation studies of prediction models.

Linda Jacqueline Elisabeth Meertens, Hubertina CJ Scheepers, Raymond G De Vries, Carmen D Dirksen, Irene Korstjens, Antonius LM Mulder, Marianne J Nieuwenhuijze, Jan G Nijhuis, Marc EA Spaanderman, Luc JM Smits

JMIR Res Protoc 2017;6(10):e203

Download Citation: END BibTex RIS

Identifying Opioid Use Disorder in the Emergency Department: Multi-System Electronic Health Record–Based Computable Phenotype Derivation and Validation Study

Approval for this study was provided by the Institutional Review Boards of the respective institutions (Protocol IDs 2000022749 [internal validation] and 18-2653 [external validation]).Clinical Definition of Opioid Use DisorderAlthough psychiatric evaluation

David Chartash, Hyung Paek, James D Dziura, Bill K Ross, Daniel P Nogee, Eric Boccio, Cory Hines, Aaron M Schott, Molly M Jeffery, Mehul D Patel, Timothy F Platts-Mills, Osama Ahmed, Cynthia Brandt, Katherine Couturier, Edward Melnick

JMIR Med Inform 2019;7(4):e15794

Download Citation: END BibTex RIS

An Innovative Artificial Intelligence–Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study

Results were calculated by averaging the results from the 5 separate experiments.GDM classification performances of the trained models were validated using the internal validation with 5-fold cross-validation and the external validation set, which was evaluated

Jiayi Shen, Jiebin Chen, Zequan Zheng, Jiabin Zheng, Zherui Liu, Jian Song, Sum Yi Wong, Xiaoling Wang, Mengqi Huang, Po-Han Fang, Bangsheng Jiang, Winghei Tsang, Zonglin He, Taoran Liu, Babatunde Akinwunmi, Chi Chiu Wang, Casper J P Zhang, Jian Huang, Wai-Kit Ming

J Med Internet Res 2020;22(9):e21573

Download Citation: END BibTex RIS

Artificial Intelligence for the Prediction of Helicobacter Pylori Infection in Endoscopic Images: Systematic Review and Meta-Analysis Of Diagnostic Test Accuracy

Enrolled studies presented performance of the AI algorithm with test dataset (internal validation), and there was no study that presented external validation performance.Among the 8 studies [9,10,21-26] included for the prediction of H pylori infection using

Chang Seok Bang, Jae Jun Lee, Gwang Ho Baik

J Med Internet Res 2020;22(9):e21983

Download Citation: END BibTex RIS

Validation of an mHealth App for Depression Screening and Monitoring (Psychologist in a Pocket): Correlational Study and Concurrence Analysis

This shows the need for validation of accuracy and reliability of published apps.The challenge of the validation process is the absence of a universal agreement on mHealth app metrics to identify high quality mobile apps, such as standardized evaluation and

Roann Munoz Ramos, Paula Glenda Ferrer Cheng, Stephan Michael Jonas

JMIR Mhealth Uhealth 2019;7(9):e12051

Download Citation: END BibTex RIS

Ensemble Learning Models Based on Noninvasive Features for Type 2 Diabetes Screening: Model Development and Validation

We separated the final dataset into three parts: the training set (80%, 2011-2014) with 3582 negative and 664 positive observations, the test set (20%, 2011-2014) with 895 negative and 165 positive observations, and the external validation set (2015-2016) with

Tianzhou Yang, Li Zhang, Liwei Yi, Huawei Feng, Shimeng Li, Haoyu Chen, Junfeng Zhu, Jian Zhao, Yingyue Zeng, Hongsheng Liu

JMIR Med Inform 2020;8(6):e15431

Download Citation: END BibTex RIS

A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study

To evaluate the performance between the feature selection model and the proposed algorithm, 10% of the target population was used as the feature selection data set, 80% as the train set, and 10% as the test set to perform a stratified 10-fold cross-validation

Wongeun Song, Se Young Jung, Hyunyoung Baek, Chang Won Choi, Young Hwa Jung, Sooyoung Yoo

JMIR Med Inform 2020;8(7):e15965

Download Citation: END BibTex RIS

Personalized Web-Based Cognitive Rehabilitation Treatments for Patients with Traumatic Brain Injury: Cluster Analysis

We included external variables that were described in previous studies such as gender, age, age ranges, education level, FIM [58], and severity at admission measured using the GCS.

Alejandro Garcia-Rudolph, Alberto Garcia-Molina, Eloy Opisso, Jose Tormos Muñoz

JMIR Med Inform 2020;8(10):e16077

Download Citation: END BibTex RIS

Classification of Depression Through Resting-State Electroencephalogram as a Novel Practice in Psychiatry: Review

There is no clear information regarding the verification of reliability of their high accuracy or internal and external validation (in terms of good generalization). Bachmann et al [16] used features for classification via logistic regression with LOOCV.

Milena Čukić, Victoria López, Juan Pavón

J Med Internet Res 2020;22(11):e19548

Download Citation: END BibTex RIS