Objective To develop a computer model to predict patients with nonalcoholic steatohepatitis (NASH) using machine learning (ML). Materials and Methods This retrospective study utilized two databases: a) the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) nonalcoholic fatty liver disease (NAFLD) adult database (2004-2009), and b) the Optum® de-identified Electronic Health Record dataset (2007-2018), a real-world dataset representative of common electronic health records in the United States. We developed an ML model to predict NASH, using confirmed NASH and non-NASH based on liver histology results in the NIDDK dataset to train the model. Results Models were trained and tested on NIDDK NAFLD data (704 patients) and the best-performing models evaluated on Optum data (~3,000,000 patients). An eXtreme Gradient Boosting model (XGBoost) consisting of 14 features exhibited high performance as measured by area under the curve (0.82), sensitivity (81%), and precision (81%) in predicting NASH. Slightly reduced performance was observed with an abbreviated feature set of 5 variables (0.79, 80%, 80%, respectively). The full model demonstrated good performance (AUC 0.76) to predict NASH in Optum data. Discussion The proposed model, named NASHmap, is the first ML model developed with confirmed NASH and non-NASH cases as determined through liver biopsy and validated on a large, real-world patient dataset. Both the 14 and 5-feature versions exhibit high performance. Conclusion The NASHmap model is a convenient and high performing tool that could be used to identify patients likely to have NASH in clinical settings, allowing better patient management and optimal allocation of clinical resources.
Real-time and high-precision localization information is vital for many modules of unmanned vehicles. At present, a high-cost RTK (Real Time Kinematic) and IMU (Integrated Measurement Unit) integrated navigation system is often used, but its accuracy cannot meet the requirements and even fails in many scenes. In order to reduce the costs and improve the localization accuracy and stability, we propose a precise and robust segmentation-based Lidar (Light Detection and Ranging) localization system aided with MEMS (Micro-Electro-Mechanical System) IMU and designed for high level autonomous driving. Firstly, we extracted features from the online frame using a series of proposed efficient low-level semantic segmentation-based multiple types feature extraction algorithms, including ground, road-curb, edge, and surface. Next, we matched the adjacent frames in Lidar odometry module and matched the current frame with the dynamically loaded pre-build feature point cloud map in Lidar localization module based on the extracted features to precisely estimate the 6DoF (Degree of Freedom) pose, through the proposed priori information considered category matching algorithm and multi-group-step L-M (Levenberg-Marquardt) optimization algorithm. Finally, the lidar localization results were fused with MEMS IMU data through a state-error Kalman filter to produce smoother and more accurate localization information at a high frequency of 200Hz. The proposed localization system can achieve 3~5 cm in position and 0.05~0.1° in orientation RMS (Root Mean Square) accuracy and outperform previous state-of-the-art systems. The robustness and adaptability have been verified with localization testing data more than 1000 Km in various challenging scenes, including congested urban roads, narrow tunnels, textureless highways, and rain-like harsh weather.
OBJECTIVE -The purpose of this study was to evaluate the effect of telephonic care management within a diabetes disease management program on adherence to treatment with hypoglycemic agents, ACE inhibitors (ACEIs), angiotensin receptor blockers (ARBs), statins, and recommended laboratory tests in a Medicaid population.RESEARCH DESIGN AND METHODS -A total of 2,598 patients with diabetes enrolled for at least 2 years in Florida: A Healthy State (FAHS), a large Medicaid disease management program, who received individualized telephonic care management were selected if they were eligible for at least 12 months before and 12 months after beginning care management. Patients were matched one-to-one on all baseline characteristics to 2,598 control patients. The impact of care management on utilization and adherence rates for diabetes-related medications and tests was analyzed with the difference-in-difference estimator.RESULTS -Changes in utilization were evaluated separately for those who were characterized as adherent to treatment at baseline ("users") and those who were not ("nonusers"). Both groups achieved significant improvement in adherence between baseline and follow-up. Nonusers increased their overall hypoglycemic use by 0.7 script (P Ͻ 0.001), by 0.7 script for ACEIs and statins (both P Ͻ 0.001), by 0.8 test for A1C (P Ͻ 0.001), and by 0.7 test for lipids (P Ͻ 0.001). Users increased hypoglycemic use by 1.5 scripts (P Ͻ 0.001) and insulin use by 0.9 script (P Ͻ 0.001).CONCLUSIONS -The FAHS telephonic care management intervention effectively induced Medicaid patients with diabetes to begin treatment and improved adherence to oral hypoglycemic agents and recommended tests. It also substantially improved adherence among baseline insulin users.
Aim Pemetrexed, a new generation antifolate drug, has been approved for the treatment of locally advanced or metastatic breast cancer. However, factors affecting its efficacy and resistance have not been fully elucidated yet. ATP-binding cassette (ABC) transporters are predictors of prognosis as well as of adverse effects of several xenobiotics. This study was designed to explore whether ABC transporters affect pemetrexed resistance and can contribute to the optimization of breast cancer treatment regimen. Methods First, we measured the expression levels of ABC transporter family members in cell lines. Subsequently, we assessed the potential role of ABC transporters in conferring resistance to pemetrexed in primary breast cancer cells isolated from 34 breast cancer patients and the role of ABCC5 in mediating pemetrexed transport and apoptotic pathways in MCF-7 cells. Finally, the influence of ABCC5 expression on the therapeutic effect of pemetrexed was evaluated in an in vivo xenograft mouse model of breast cancer. Results The expression levels of ABCC2, ABCC4, ABCC5, and ABCG2 significantly increased in the pan-resistant cell line, and the ABCC5 level in the MCF-7-ADR cell line was 5.21 times higher than that in the control group. ABCC5 expression was inversely correlated with pemetrexed sensitivity (IC50, r = 0.741; p < 0.001) in breast cancer cells derived from 34 patients. Furthermore, we found that the expression level of ABCC5 influenced the efflux and cytotoxicity of pemetrexed in MCF-7 cells, with IC50 values of 0.06 and 0.20 μg/mL in ABCC5 knockout and over-expression cells, respectively. In the in vivo study, we observed that ABCC5 affected the sensitivity of pemetrexed in breast tumor-bearing mice, and the tumor volume was much larger in the ABCC5-overexpressing group than in the control group when compared with their own initial volumes (2.7-fold vs. 1.3-fold). Conclusions Our results indicated that ABCC5 expression was associated with pemetrexed resistance in vitro and in vivo, and it may serve as a target or biomarker for the optimization of pemetrexed regimen in breast cancer treatment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.