Setting up of a machine learning algorithm for the identification of severe liver fibrosis profile in the general US population cohort

Machine learning in public health informatics: Evidence that complex sampling structures may not be needed for prediction models with imbalanced outcomes

PURPOSE

The objective of this study is to investigate the predictive ability of machine learning models for imbalanced outcomes from national survey data without the use of sampling weights.

METHODS

We evaluated the predictive performance of machine learning models on imbalanced outcomes from the US National Health and Nutrition Examination Survey (USNHANES) without using sampling weights. Four machine learning models (support vector machine, random forest, least absolute shrinkage and selection operator regression, and deep neural network) were compared with a logistic model that incorporates the survey's complex sampling design. Three resampling methods (oversampling, undersampling, and combined) were used to address class imbalance during the model training process.

RESULTS

For all models, the balanced accuracy was similar (ranging from 0.72 to 0.76) and the specificity was smaller than sensitivity except for random forest. The support vector machine and neural networks performed best with sensitivity (ranging from 0.79 to 0.83), while the random forest had the largest specificity (ranging from 0.86 to 0.96), with one exception. PR-AUC scores and Brier scores were low ranging from 0.2529 to 0.3313 (lower scores worse) and 0.1005-0.3245 (lower scores better), respectively CONCLUSIONS: The machine learning models had overall similar predictive capacity to the recommended methods which integrate the complex sampling design for the prediction of osteoarthritis occurrence with USNHANES.

Metabolic Dysfunction-Associated Fibrosis 5 (MAF-5) Score Predicts Liver Fibrosis Risk and Outcome in the General Population With Metabolic Dysfunction

BACKGROUND & AIMS

There is an unmet need for noninvasive tests to improve case-finding and aid primary care professionals in referring patients at high risk of liver disease.

METHODS

A metabolic dysfunction-associated fibrosis (MAF-5) score was developed and externally validated in a total of 21,797 individuals with metabolic dysfunction in population-based (National Health and Nutrition Examination Survey 2017-2020, National Health and Nutrition Examination Survey III, and Rotterdam Study) and hospital-based (from Antwerp and Bogota) cohorts. Fibrosis was defined as liver stiffness ≥8.0 kPa. Diagnostic accuracy was compared with FIB-4, nonalcoholic fatty liver disease fibrosis score (NFS), LiverRisk score and steatosis-associated fibrosis estimator (SAFE). MAF-5 was externally validated with liver stiffness measurement ≥8.0 kPa, with shear-wave elastography ≥7.5 kPa, and biopsy-proven steatotic liver disease according to Metavir and Nonalcoholic Steatohepatitis Clinical Research Network scores, and was tested for prognostic performance (all-cause mortality).

RESULTS

The MAF-5 score comprised waist circumference, body mass index (calculated as kg / m2), diabetes, aspartate aminotransferase, and platelets. With this score, 60.9% was predicted at low, 14.1% at intermediate, and 24.9% at high risk of fibrosis. The observed prevalence was 3.3%, 7.9%, and 28.1%, respectively. The area under the receiver operator curve of MAF-5 (0.81) was significantly higher than FIB-4 (0.61), and outperformed the FIB-4 among young people (negative predictive value [NPV], 99%; area under the curve [AUC], 0.86 vs NPV, 94%; AUC, 0.51) and older adults (NPV, 94%; AUC, 0.75 vs NPV, 88%; AUC, 0.55). MAF-5 showed excellent performance to detect liver stiffness measurement ≥12 kPa (AUC, 0.86 training; AUC, 0.85 validation) and good performance in detecting liver stiffness and biopsy-proven liver fibrosis among the external validation cohorts. MAF-5 score >1 was associated with increased risk of all-cause mortality in (un)adjusted models (adjusted hazard ratio, 1.59; 95% CI, 1.47-1.73).

CONCLUSIONS

The MAF-5 score is a validated, age-independent, inexpensive referral tool to identify individuals at high risk of liver fibrosis and all-cause mortality in primary care populations, using simple variables.

NAIF: A novel artificial intelligence-based tool for accurate diagnosis of stage F3/F4 liver fibrosis in the general adult population, validated with three external datasets

OBJECTIVE

The purpose of this study was to determine the effectiveness of a new AI-based tool called NAIF (NAFLD-AI-Fibrosis) in identifying individuals from the general population with advanced liver fibrosis (stage F3/F4). We compared NAIF's performance to two existing risk score calculators, aspartate aminotransferase-to-platelet ratio index (APRI) and fibrosis-4 (Fib4).

METHODS

To set up the algorithm for diagnosing severe liver fibrosis (defined as Fibroscan® values E ≥ 9.7 KPa), we used 19 blood biochemistry parameters and two demographic parameters in a group of 5,962 individuals from the NHANES population (2017-2020 pre-pandemic, public database). We then assessed the algorithm's performance by comparing its accuracy, precision, sensitivity, specificity, and F1 score values to those of APRI and Fib4 scoring systems.

RESULTS

In a kept-out sub dataset of the NHANES population, NAIF achieved a predictive precision of 72 %, a sensitivity of 61 %, and a specificity of 77 % in correctly identifying adults (aged 18-79 years) with severe liver fibrosis. Additionally, NAIF performed well when tested with two external datasets of Italian patients with a Fibroscan® score E ≥ 9.7 kPa, and with an external dataset of patients with diagnosis of severe liver fibrosis through biopsy.

CONCLUSIONS

The results of our study suggest that NAIF, using routinely available parameters, outperforms in sensitivity existing scoring methods (Fib4 and APRI) in diagnosing severe liver fibrosis, even when tested with external validation datasets. NAIF uses routinely available parameters, making it a promising tool for identifying individuals with advanced liver fibrosis from the general population. Word count abstract: 236.

Exploring the State of Machine Learning and Deep Learning in Medicine: A Survey of the Italian Research Community

Artificial intelligence (AI) is becoming increasingly important, especially in the medical field. While AI has been used in medicine for some time, its growth in the last decade is remarkable. Specifically, machine learning (ML) and deep learning (DL) techniques in medicine have been increasingly adopted due to the growing abundance of health-related data, the improved suitability of such techniques for managing large datasets, and more computational power. ML and DL methodologies are fostering the development of new “intelligent” tools and expert systems to process data, to automatize human–machine interactions, and to deliver advanced predictive systems that are changing every aspect of the scientific research, industry, and society. The Italian scientific community was instrumental in advancing this research area. This article aims to conduct a comprehensive investigation of the ML and DL methodologies and applications used in medicine by the Italian research community in the last five years. To this end, we selected all the papers published in the last five years with at least one of the authors affiliated to an Italian institution that in the title, in the abstract, or in the keywords present the terms “machine learning” or “deep learning” and reference a medical area. We focused our research on journal papers under the hypothesis that Italian researchers prefer to present novel but well-established research in scientific journals. We then analyzed the selected papers considering different dimensions, including the medical topic, the type of data, the pre-processing methods, the learning methods, and the evaluation methods. As a final outcome, a comprehensive overview of the Italian research landscape is given, highlighting how the community has increasingly worked on a very heterogeneous range of medical problems.

Prediction of Fatty Liver Disease in a Chinese Population Using Machine-Learning Algorithms

BACKGROUND

Fatty liver disease (FLD) is an important risk factor for liver cancer and cardiovascular disease and can lead to significant social and economic burden. However, there is currently no nationwide epidemiological survey for FLD in China, making early FLD screening crucial for the Chinese population. Unfortunately, liver biopsy and abdominal ultrasound, the preferred methods for FLD diagnosis, are not practical for primary medical institutions. Therefore, the aim of this study was to develop machine learning (ML) models for screening individuals at high risk of FLD, and to provide a new perspective on early FLD diagnosis.

METHODS

This study included a total of 30,574 individuals between the ages of 18 and 70 who completed abdominal ultrasound and the related clinical examinations. Among them, 3474 individuals were diagnosed with FLD by abdominal ultrasound. We used 11 indicators to build eight classification models to predict FLD. The model prediction ability was evaluated by the area under the curve, sensitivity, specificity, positive predictive value, negative predictive value, and kappa value. Feature importance analysis was assessed by Shapley value or root mean square error loss after permutations.

RESULTS

Among the eight ML models, the prediction accuracy of the extreme gradient boosting (XGBoost) model was highest at 89.77%. By feature importance analysis, we found that the body mass index, triglyceride, and alanine aminotransferase play important roles in FLD prediction.

CONCLUSION

XGBoost improves the efficiency and cost of large-scale FLD screening.