A Review on Human-AI Interaction in Machine Learning and Insights for Medical Applications.

OBJECTIVE: To provide a human-Artificial Intelligence (AI) interaction review for Machine Learning (ML) applications to inform how to best combine both human domain expertise and computational power of ML methods. The review focuses on the medical field, as the medical ML application literature highlights a special necessity of medical experts collaborating with ML approaches. METHODS: A scoping literature review is performed on Scopus and Google Scholar using the terms "human in the loop", "human in the loop machine learning", and "interactive machine learning". Peer-reviewed papers published from 2015 to 2020 are included in our review. RESULTS: We design four questions to investigate and describe human-AI interaction in ML applications. These questions are "Why should humans be in the loop?", "Where does human-AI interaction occur in the ML processes?", "Who are the humans in the loop?", and "How do humans interact with ML in Human-In-the-Loop ML (HILML)?". To answer the first question, we describe three main reasons regarding the importance of human involvement in ML applications. To address the second question, human-AI interaction is investigated in three main algorithmic stages: 1. data producing and pre-processing; 2. ML modelling; and 3. ML evaluation and refinement. The importance of the expertise level of the humans in human-AI interaction is described to answer the third question. The number of human interactions in HILML is grouped into three categories to address the fourth question. We conclude the paper by offering a discussion on open opportunities for future research in HILML.

Nonalcoholic Fatty Liver: The Association with Metabolic Abnormalities, Body Mass Index and Central Obesity--A Population-Based Study.

BACKGROUND: To assess the prevalence of nonalcoholic fatty liver (NAFL) in Iran and to evaluate correlates of NAFL in categories of body mass index (BMI). METHODS: Using a cluster random sampling approach, 7723 subjects over 18 years of age underwent abdominal ultrasonography, laboratory evaluations, blood pressure, and anthropometric measurements and were interviewed to obtain baseline characteristics. Prevalence of NAFL according to BMI and waist to hip ratio and its association with metabolic abnormalities in categories of BMI were assessed in multivariate analysis. RESULTS: The overall prevalence of NAFL was 35.2% [95% confidence interval (CI) 34.1-36.3]. A significant number of subjects with BMI < 30 had NAFL [22.1% (CI 21.0-23.2)]. Waist to hip ratio for 38.2% (CI 35.6-40.8) of the subjects with NAFL, and BMI < 30 was higher than normal values. The odds ratio for association of NAFL and dyslipidemias were higher in subjects with BMI < 30 versus those with BMI ≥ 30: (1) hypertriglyceridemia: 2.21 vs. 1.57, P = 0.006; (2) lower high-density lipoprotein: 1.29 versus 0.98, P = 0.046. Higher low-density lipoprotein also revealed greater association with NAFL in subjects with BMI < 25 than those with BMI ≥ 25 (odds ratio 1.84 vs. 1.1, P = 0.015). CONCLUSIONS: NAFL shows stronger association with central obesity compared to high BMI. NAFL has stronger association with dyslipidemias in subjects with low compared with high BMI.