Publications by authors named "Sheojung Shin"

2 Publications

  • Page 1 of 1

Machine learning vs. conventional statistical models for predicting heart failure readmission and mortality.

ESC Heart Fail 2021 Feb 17;8(1):106-115. Epub 2020 Nov 17.

University of Toronto, ICES, Rm G-106, 2075 Bayview Ave., Toronto, ON, M4G2E1, Canada.

Aims: This study aimed to review the performance of machine learning (ML) methods compared with conventional statistical models (CSMs) for predicting readmission and mortality in patients with heart failure (HF) and to present an approach to formally evaluate the quality of studies using ML algorithms for prediction modelling.

Methods And Results: Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we performed a systematic literature search using MEDLINE, EPUB, Cochrane CENTRAL, EMBASE, INSPEC, ACM Library, and Web of Science. Eligible studies included primary research articles published between January 2000 and July 2020 comparing ML and CSMs in mortality and readmission prognosis of initially hospitalized HF patients. Data were extracted and analysed by two independent reviewers. A modified CHARMS checklist was developed in consultation with ML and biostatistics experts for quality assessment and was utilized to evaluate studies for risk of bias. Of 4322 articles identified and screened by two independent reviewers, 172 were deemed eligible for a full-text review. The final set comprised 20 articles and 686 842 patients. ML methods included random forests (n = 11), decision trees (n = 5), regression trees (n = 3), support vector machines (n = 9), neural networks (n = 12), and Bayesian techniques (n = 3). CSMs included logistic regression (n = 16), Cox regression (n = 3), or Poisson regression (n = 3). In 15 studies, readmission was examined at multiple time points ranging from 30 to 180 day readmission, with the majority of studies (n = 12) presenting prediction models for 30 day readmission outcomes. Of a total of 21 time-point comparisons, ML-derived c-indices were higher than CSM-derived c-indices in 16 of the 21 comparisons. In seven studies, mortality was examined at 9 time points ranging from in-hospital mortality to 1 year survival; of these nine, seven reported higher c-indices using ML. Two of these seven studies reported survival analyses utilizing random survival forests in their ML prediction models. Both reported higher c-indices when using ML compared with CSMs. A limitation of studies using ML techniques was that the majority were not externally validated, and calibration was rarely assessed. In the only study that was externally validated in a separate dataset, ML was superior to CSMs (c-indices 0.913 vs. 0.835).

Conclusions: ML algorithms had better discrimination than CSMs in most studies aiming to predict risk of readmission and mortality in HF patients. Based on our review, there is a need for external validation of ML-based studies of prediction modelling. We suggest that ML-based studies should also be evaluated using clinical quality standards for prognosis research. Registration: PROSPERO CRD42020134867.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
February 2021

APP21 transgenic rats develop age-dependent cognitive impairment and microglia accumulation within white matter tracts.

J Neuroinflammation 2018 Aug 28;15(1):241. Epub 2018 Aug 28.

Vulnerable Brain Laboratory, Department of Anatomy and Cell Biology, Schulich School of Medicine and Dentistry, University of Western Ontario, 1151 Richmond St, London, Ontario, N6A 5C1, Canada.

Background: Most of the animal models commonly used for preclinical research into Alzheimer's disease (AD) largely fail to address the pathophysiology, including the impact of known risk factors, of the widely diagnosed sporadic form of the disease. Here, we use a transgenic rat (APP21) that does not develop AD-like pathology spontaneously with age, but does develop pathology following vascular stress. To further the potential of this novel rat model as a much-needed pre-clinical animal model of sporadic AD, we characterize APP21 transgenic rats behaviorally and histologically up to 19 months of age.

Methods: The open field test was used as a measure of activity; and the Morris water maze was used to assess learning, memory, and strategy shift. Neuronal loss and microglia activation were also assessed throughout the brain.

Results: APP21 transgenic rats showed deficits in working memory from an early age, yet memory recall performance after 24 and 72 h was equal to that of wildtype rats and did not deteriorate with age. A deficit in strategy shift was observed at 19 months of age in APP21 transgenic rats compared to Fischer wildtype rats. Histologically, APP21 transgenic rats demonstrated accelerated white matter inflammation compared to wildtype rats, but interestingly no differences in neuron loss were observed.

Conclusions: The combined presence of white matter pathology and executive function deficits mirrored what is often found in patients with mild cognitive impairment or early dementia, and suggests that this rat model will be useful for translationally meaningful studies into the development and prevention of sporadic AD. The presence of widespread white matter inflammation as the only observed pathological correlate for cognitive deficits raises new questions as to the role of neuroinflammation in cognitive decline.
View Article and Find Full Text PDF

Download full-text PDF

Source Listing
August 2018