Current-Visit and Next-Visit Prediction for Fatty Liver Disease With a Large-Scale Dataset: Model Development and Performance Comparison.

BACKGROUND: Fatty liver disease (FLD) arises from the accumulation of fat in the liver and may cause liver inflammation, which, if not well controlled, may develop into liver fibrosis, cirrhosis, or even hepatocellular carcinoma. OBJECTIVE: We describe the construction of machine-learning models for current-visit prediction (CVP), which can help physicians obtain more information for accurate diagnosis, and next-visit prediction (NVP), which can help physicians provide potential high-risk patients with advice to effectively prevent FLD. METHODS: The large-scale and high-dimensional dataset used in this study comes from Taipei MJ Health Research Foundation in Taiwan. We used one-pass ranking and sequential forward selection (SFS) for feature selection in FLD prediction. For CVP, we explored multiple models, including k-nearest-neighbor classifier (KNNC), Adaboost, support vector machine (SVM), logistic regression (LR), random forest (RF), Gaussian naïve Bayes (GNB), decision trees C4.5 (C4.5), and classification and regression trees (CART). For NVP, we used long short-term memory (LSTM) and several of its variants as sequence classifiers that use various input sets for prediction. Model performance was evaluated based on two criteria: the accuracy of the test set and the intersection over union/coverage between the features selected by one-pass ranking/SFS and by domain experts. The accuracy, precision, recall, F-measure, and area under the receiver operating characteristic curve were calculated for both CVP and NVP for males and females, respectively. RESULTS: After data cleaning, the dataset included 34,856 and 31,394 unique visits respectively for males and females for the period 2009-2016. The test accuracy of CVP using KNNC, Adaboost, SVM, LR, RF, GNB, C4.5, and CART was respectively 84.28%, 83.84%, 82.22%, 82.21%, 76.03%, 75.78%, and 75.53%. The test accuracy of NVP using LSTM, bidirectional LSTM (biLSTM), Stack-LSTM, Stack-biLSTM, and Attention-LSTM was respectively 76.54%, 76.66%, 77.23%, 76.84%, and 77.31% for fixed-interval features, and was 79.29%, 79.12%, 79.32%, 79.29%, and 78.36%, respectively, for variable-interval features. CONCLUSIONS: This study explored a large-scale FLD dataset with high dimensionality. We developed FLD prediction models for CVP and NVP. We also implemented efficient feature selection schemes for current- and next-visit prediction to compare the automatically selected features with expert-selected features. In particular, NVP emerged as more valuable from the viewpoint of preventive medicine. For NVP, we propose use of feature set 2 (with variable intervals), which is more compact and flexible. We have also tested several variants of LSTM in combination with two feature sets to identify the best match for male and female FLD prediction. More specifically, the best model for males was Stack-LSTM using feature set 2 (with 79.32% accuracy), whereas the best model for females was LSTM using feature set 1 (with 81.90% accuracy).

Hypoxia-induced therapeutic neovascularization in a mouse model of an ischemic limb using cell aggregates composed of HUVECs and cbMSCs.

Cell transplantation for therapeutic neovascularization holds great promise for treating ischemic diseases. This work prepared three-dimensional aggregates of human umbilical vein endothelial cells (HUVECs) and cord-blood mesenchymal stem cells (cbMSCs) with different levels of internal hypoxia by a methylcellulose hydrogel system. We found that few apoptosis occurred in these cell aggregates, despite developing a hypoxic microenvironment in their inner cores. Via effectively switching on the hypoxia-inducible factor-1α-dependent angiogenic mechanisms, culturing the internally hypoxic HUVEC/cbMSC aggregates on Matrigel resulted in formation of extensive and persistent tubular networks and significant upregulation of pro-angiogenic genes. As the level of internal hypoxia created in cell aggregates increased, the robustness of the tubular structures developed on Matrigel increased, and expression levels of the pro-angiogenic genes also elevated. Transplantation of hypoxic HUVEC/cbMSC aggregates into a mouse model of an ischemic limb significantly promoted formation of functional vessels, improved regional blood perfusion, and attenuated muscle atrophy and bone losses, thereby rescuing tissue degeneration. Notably, their therapeutic efficacy was clearly dependent upon the level of internal hypoxia established in cell aggregates. These analytical results demonstrate that by establishing a hypoxic environment in HUVEC/cbMSC aggregates, their potential for therapeutic neovascularization can be markedly enhanced.

Intramuscular delivery of 3D aggregates of HUVECs and cbMSCs for cellular cardiomyoplasty in rats with myocardial infarction.

Cell-based therapeutic neovascularization is a promising method for treating ischemic disorders. In this work, human umbilical vein endothelial cells (HUVECs) were thoroughly premixed with cord-blood mesenchymal stem cells (cbMSCs) and cultivated to form three-dimensional (3D) cell aggregates for cellular cardiomyoplasty. In the in vitro study, tubular networks were formed at day 1 after the co-culturing of dissociated HUVECs and cbMSCs on Matrigel; however, as time progressed, the grown tubular networks regressed severely. Conversely, when 3D cell aggregates were grown on Matrigel, mature and stable tubular networks were observed over time, under the influence of their intensive cell-extracellular matrix (ECM) interactions and cell-cell contacts. 3D cell aggregates were transplanted into the peri-infarct zones of rats with myocardial infarction (MI) via direct intramyocardial injection. Based on our pinhole single photon emission computed tomography (SPECT) myocardial-perfusion observations, echocardiographic heart-function examinations and histological analyses, the engrafted 3D cell aggregates considerably enhanced the vascular densities and the blood flow recovery in the ischemic myocardium over those of their dissociated counterparts, thereby reducing the size of perfusion defects and restoring cardiac function. These results demonstrate that the intramuscular delivery of 3D cell aggregates of HUVECs/cbMSCs can be a valuable cell-based regenerative therapeutic strategy against MI.

Three-dimensional cell aggregates composed of HUVECs and cbMSCs for therapeutic neovascularization in a mouse model of hindlimb ischemia.

The proximity of cells in three-dimensional (3D) organization maximizes the cell-cell communication and signaling that are critical for cell function. In this study, 3D cell aggregates composed of human umbilical vein endothelial cells (HUVECs) and cord-blood mesenchymal stem cells (cbMSCs) were used for therapeutic neovascularization to rescue tissues from critical limb ischemia. Within the cell aggregates, homogeneously mixed HUVECs and cbMSCs had direct cell-cell contact with expressions of endogenous extracellular matrices and adhesion molecules. Although dissociated HUVECs/cbMSCs initially formed tubular structures on Matrigel, the grown tubular network substantially regressed over time. Conversely, 3D HUVEC/cbMSC aggregates seeded on Matrigel exhibited an extensive tubular network that continued to expand without regression. Immunostaining experiments show that, by differentiating into smooth muscle cell (SMC) lineages, the cbMSCs stabilize the HUVEC-derived tubular network. The real-time PCR analysis results suggest that, through myocardin, TGF-ß signaling regulates the differentiation of cbMSCs into SMCs. Transplantation of 3D HUVEC/cbMSC aggregates recovered blood perfusion in a mouse model of hindlimb ischemia more effectively compared to their dissociated counterparts. The experimental results confirm that the transplanted 3D HUVEC/cbMSC aggregates enhanced functional vessel formation within the ischemic limb and protected it from degeneration. The 3D HUVEC/cbMSC aggregates can therefore facilitate the cell-based therapeutic strategies for modulating postnatal neovascularization.