Yi-Ju Tseng is an associate professor at National Central University Digital Health Lab with extensive experience in claims data and electronic medical records analysis and data mining analytics. Her work focuses on improving infection surveillance by using informatics techniques and applying data mining technology to clinical research.
Download my CV.
PhD in Biomedical Electronics and Bioinformatics, 2013
National Taiwan University
BSc in Clinical Laboratory Sciences and Medical Biotechnology, 2008
National Taiwan University
BackgroundApproximately 10%–15% of patients with breast cancer die of cancer metastasis or recurrence, and early diagnosis of it can improve prognosis. Breast cancer outcomes may be prognosticated on the basis of surface markers of tumor cells and serum tests. However, evaluation of a combination of clinicopathological features may offer a more comprehensive overview for breast cancer prognosis. Materials and methods We evaluated serum human epidermal growth factor receptor 2 (sHER2) as part of a combination of clinicopathological features used to predict breast cancer metastasis using machine learning algorithms, namely random forest, support vector machine, logistic regression, and Bayesian classification algorithms. The sample cohort comprised 302 patients who were diagnosed with and treated for breast cancer and received at least one sHER2 test at Chang Gung Memorial Hospital at Linkou between 2003 and 2016. Results The random-forest-based model was determined to be the optimal model to predict breast cancer metastasis at least 3 months in advance; the corresponding the area under the receiver operating characteristic curve value was 0. 75 (p < 0. 001). Conclusion The random-forest-based model presented in this study may be helpful as part of a follow-up intervention decision support system and may lead to early detection of recurrence, early treatment, and more favorable outcomes.
Heterogeneous vancomycin-intermediate Staphylococcus aureus (hVISA) is an emerging superbug with implicit drug resistance to vancomycin. Detecting hVISA can guide the correct administration of antibiotics. However, hVISA cannot be detected in most clinical microbiology laboratories because the required diagnostic tools are either expensive, time consuming, or labor intensive. By contrast, matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) is a cost-effective and rapid tool that has potential for providing antibiotics resistance information. To analyze complex MALDI-TOF mass spectra, machine learning (ML) algorithms can be used to generate robust hVISA detection models. In this study, MALDI-TOF mass spectra were obtained from 35 hVISA/vancomycin-intermediate S. aureus (VISA) and 90 vancomycin-susceptible S. aureus isolates. The vancomycin susceptibility of the isolates was determined using an Etest and modified population analysis profile–area under the curve. ML algorithms, namely a decision tree, k-nearest neighbors, random forest, and a support vector machine (SVM), were trained and validated using nested cross-validation to provide unbiased validation results. The area under the curve of the models ranged from 0.67 to 0.79, and the SVM-derived model outperformed those of the other algorithms. The peaks at m/z 1132, 2895, 3176, and 6591 were noted as informative peaks for detecting hVISA/VISA. We demonstrated that hVISA/VISA could be detected by analyzing MALDI-TOF mass spectra using ML. Moreover, the results are particularly robust due to a strict validation method. The ML models in this study can provide rapid and accurate reports regarding hVISA/VISA and thus guide the correct administration of antibiotics in treatment of S. aureus infection.
OBJECTIVE The American Diabetes Association recommends metformin as first-line therapy for type 2 diabetes. However, nonadherence to antihyperglycemic medication is common, and a clinician could confuse nonadherence with pharmacologic failure, potentially leading to premature prescribing of second-line therapies. We measured metformin use before second-line therapy initialization. RESEARCH DESIGN AND METHODS This retrospective cross-sectional study used unidentifiable member claims data from individuals covered from 2010 to 2015 by Aetna, a U.S. health benefits company. Beneficiaries with two physician claims or one hospitalization with a type 2 diabetes diagnosis were included. Recommended use of metformin was measured by the proportion of days covered over 60 days. Through sensitivity analysis, we varied estimates of the percentage of beneficiaries who used low-cost generic prescription medication programs. RESULTS A total of 52,544 individuals with type 2 diabetes were eligible. Of 22,956 patients given second-line treatment, only 1,875 (8.2%) had evidence of recommended use of metformin in the prior 60 days, and 6,441 (28.0%) had no prior claims evidence of having taken metformin. At the top range of sensitivity, only 49.5% patients could have had recommended use. Patients were more likely to be given an additional second-line antihyperglycemic medication or insulin if they were given their initial second-line medication without evidence of recommended use of metformin (P < 0.001). CONCLUSIONS Despite published guidelines, second-line therapy often is initiated without evidence of recommended use of first-line therapy. Apparent treatment failures, which may in fact be attributable to nonadherence to guidelines, are common. Point-of-care and population-level processes are needed to monitor and improve guideline adherence.