Dataset Information

The TVGH-NYCU Thal-Classifier: Development of a Machine-Learning Classifier for Differentiating Thalassemia and Non-Thalassemia Patients.

ABSTRACT: Thalassemia and iron deficiency are the most common etiologies for microcytic anemia and there are indices discriminating both from common laboratory simple automatic counters. In this study a new classifier for discriminating thalassemia and non-thalassemia microcytic anemia was generated via combination of exciting indices with machine-learning techniques. A total of 350 Taiwanese adult patients whose anemia diagnosis, complete blood cell counts, and hemoglobin gene profiles were retrospectively reviewed. Thirteen prior established indices were applied to current cohort and the sensitivity, specificity, positive and negative predictive values were calculated. A support vector machine (SVM) with Monte-Carlo cross-validation procedure was adopted to generate the classifier. The performance of our classifier was compared with original indices by calculating the average classification error rate and area under the curve (AUC) for the sampled datasets. The performance of this SVM model showed average AUC of 0.76 and average error rate of 0.26, which surpassed all other indices. In conclusion, we developed a convenient tool for primary-care physicians when deferential diagnosis contains thalassemia for the Taiwanese adult population. This approach needs to be validated in other studies or bigger database.

SUBMITTER: Fu YK

PROVIDER: S-EPMC8467438 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The TVGH-NYCU Thal-Classifier: Development of a Machine-Learning Classifier for Differentiating Thalassemia and Non-Thalassemia Patients.

Fu Yi-Kai YK Liu Hsueng-Mei HM Lee Li-Hsuan LH Chen Ying-Ju YJ Chien Sheng-Hsuan SH Lin Jeong-Shi JS Chen Wen-Chun WC Cheng Ming-Hsuan MH Lin Po-Heng PH Lai Jheng-You JY Chen Chyong-Mei CM Liu Chun-Yu CY

Diagnostics (Basel, Switzerland) 20210920 9

Thalassemia and iron deficiency are the most common etiologies for microcytic anemia and there are indices discriminating both from common laboratory simple automatic counters. In this study a new classifier for discriminating thalassemia and non-thalassemia microcytic anemia was generated via combination of exciting indices with machine-learning techniques. A total of 350 Taiwanese adult patients whose anemia diagnosis, complete blood cell counts, and hemoglobin gene profiles were retrospective ...[more]

PMID: 34574066

Similar Datasets

Project description:BackgroundOpioid misuse screening in hospitals is resource-intensive and rarely done. Many hospitalized patients are never offered opioid treatment. An automated approach leveraging routinely captured electronic health record (EHR) data may be easier for hospitals to institute. We previously derived and internally validated an opioid classifier in a separate hospital setting. The aim is to externally validate our previously published and open-source machine-learning classifier at a different hospital for identifying cases of opioid misuse.MethodsAn observational cohort of 56,227 adult hospitalizations was examined between October 2017 and December 2019 during a hospital-wide substance use screening program with manual screening. Manually completed Drug Abuse Screening Test served as the reference standard to validate a convolutional neural network (CNN) classifier with coded word embedding features from the clinical notes of the EHR. The opioid classifier utilized all notes in the EHR and sensitivity analysis was also performed on the first 24 h of notes. Calibration was performed to account for the lower prevalence than in the original cohort.ResultsManual screening for substance misuse was completed in 67.8% (n = 56,227) with 1.1% (n = 628) identified with opioid misuse. The data for external validation included 2,482,900 notes with 67,969 unique clinical concept features. The opioid classifier had an AUC of 0.99 (95% CI 0.99-0.99) across the encounter and 0.98 (95% CI 0.98-0.99) using only the first 24 h of notes. In the calibrated classifier, the sensitivity and positive predictive value were 0.81 (95% CI 0.77-0.84) and 0.72 (95% CI 0.68-0.75). For the first 24 h, they were 0.75 (95% CI 0.71-0.78) and 0.61 (95% CI 0.57-0.64).ConclusionsOur opioid misuse classifier had good discrimination during external validation. Our model may provide a comprehensive and automated approach to opioid misuse identification that augments current workflows and overcomes manual screening barriers.

Dataset Information

The TVGH-NYCU Thal-Classifier: Development of a Machine-Learning Classifier for Differentiating Thalassemia and Non-Thalassemia Patients.

Publications

The TVGH-NYCU Thal-Classifier: Development of a Machine-Learning Classifier for Differentiating Thalassemia and Non-Thalassemia Patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets