Dietary assessment can be crucial for the overall well-being of humans and at least in some instances for the prevention and management of chronic, life-threatening diseases. Recall and manual record keeping methods for food intake monitoring are available, but often inaccurate when applied for a long period of time. On the other hand, automatic record keeping approaches that adopt mobile cameras and computer vision methods seem to simplify the process and can improve current human-centric diet monitoring methods. Here we present an extended critical literature overview of image-based food recognition systems (IBFRS) combining a camera of the user's mobile device with computer vision methods and publicly available food datasets (PAFD). In brief, such systems consist of several phases, such as the segmentation of the food items on the plate, the classification of the food items in a specific food category, and the estimation phase of volume, calories or nutrients of each food item. 159 studies were screened in this systematic review of IBFRS. A detailed overview of the methods adopted in each of the 78 included studies of this systematic review of IBFRS is provided along with their performance on PAFD. Studies that included IBFRS without presenting their performance in at least one of the abovementioned phases were excluded. Among the included studies, 45 (58%) studies adopted deep learning methods and especially Convolutional Neural Networks (CNNs) in at least one phase of the IBFRS with input PAFD. Among the implemented techniques, CNNs outperform all other approaches on the PAFD with a large volume of data, since the richness of these datasets provides adequate training resources for such algorithms. We also present evidence for the benefits of application of IBFRS in professional dietetic practice. Furthermore, challenges related to the IBFRS presented here are also thoroughly discussed along with future directions.

An interpretable machine learning (ML) framework is introduced to enhance the diagnosis of Mild Cognitive Impairment (MCI) and Alzheimer’s disease (AD) by ensuring robustness of the ML models’ interpretations. The dataset used comprises volumetric measurements from brain MRI and genetic data from healthy individuals and patients with MCI/AD, obtained through the Alzheimer’s Disease Neuroimaging Initiative. The existing class imbalance is addressed by an ensemble learning approach, while various attribution-based and counterfactual-based interpretability methods are leveraged towards producing diverse explanations related to the pathophysiology of MCI/AD. A unification method combining SHAP with counterfactual explanations assesses the interpretability techniques’ robustness. The best performing model yielded 87.5% balanced accuracy and 90.8% F1-score. The attribution-based interpretability methods highlighted significant volumetric and genetic features related to MCI/AD risk. The unification method provided useful insights regarding those features’ necessity and sufficiency, further showcasing their significance in MCI/AD diagnosis.

Early detection of breast cancer is a powerful tool towards decreasing its socioeconomic burden. Although, artificial intelligence (AI) methods have shown remarkable results towards this goal, their "black box" nature hinders their wide adoption in clinical practice. To address the need for AI guided breast cancer diagnosis, interpretability methods can be utilized. In this study, we used AI methods, i.e., Random Forests (RF), Neural Networks (NN) and Ensembles of Neural Networks (ENN), towards this goal and explained and optimized their performance through interpretability techniques, such as the Global Surrogate (GS) method, the Individual Conditional Expectation (ICE) plots and the Shapley values (SV). The Wisconsin Diagnostic Breast Cancer (WDBC) dataset of the open UCI repository was used for the training and evaluation of the AI algorithms. The best performance for breast cancer diagnosis was achieved by the proposed ENN (96.6% accuracy and 0.96 area under the ROC curve), and its predictions were explained by ICE plots, proving that its decisions were compliant with current medical knowledge and can be further utilized to gain new insights in the pathophysiological mechanisms of breast cancer. Feature selection based on features’ importance according to the GS model improved the performance of the RF (leading the accuracy from 96.49% to 97.18% and the area under the ROC curve from 0.96 to 0.97) and feature selection based on features’ importance according to SV improved the performance of the NN (leading the accuracy from 94.6% to 95.53% and the area under the ROC curve from 0.94 to 0.95). Compared to other approaches on the same dataset, our proposed models demonstrated state of the art performance while being interpretable.

The purpose of this study is to present a hybrid approach based on the combined use of a genetic algorithm (GA) and a nearest neighbours classifier for the selection of the critical clinical features which are strongly related with the incidence of fatal and non fatal Cardiovascular Disease (CVD) in patients with Type 2 Diabetes Mellitus (T2DM). For the development and the evaluation of the proposed algorithm, data from the medical records of 560 patients with T2DM are used. The best subsets of features proposed by the implemented algorithm include the most common risk factors, such as age at diagnosis, duration of diagnosed diabetes, glycosylated haemoglobin (HbA1c), cholesterol concentration, and smoking habit, but also factors related to the presence of other diabetes complications and the use of antihypertensive and diabetes treatment drugs (i.e. proteinuria, calcium antagonists, b-blockers, diguanides and insulin). The obtained results demonstrate that the best performance was achieved when the weighted k-nearest neighbours classifier was applied to the CVD dataset with the best subset of features selected by the GA, which resulted in high levels of accuracy (0.96), sensitivity (0.80) and specificity (0.98).

The use of capillary blood 3-β-hydroxybutyrate (3HB) is a more precise method than urine ketones measurement for the diagnosis of diabetic ketoacidosis. Fasting ketonuria is common during normal pregnancy, while there is evidence that it is increased among pregnant women with Gestational Diabetes Mellitus (GDM) who are on a diet. 3HB levels have been related to impaired offspring psychomotor development. Reports with concomitant measurement of blood and urine ketones in women with GDM who followed a balanced diet are lacking. To compare the prevalence of fasting ketonemia and ketonuria in women with GDM following the Institute of Medicine diet instructions and assess their possible relation with metabolic parameters and therapeutic interventions. 180 women with GDM were studied. In each patient, in successive visits, capillary blood and urine ketones were simultaneously measured. The total measurements were 378, while the average number of measurements per patient was 2.1. The prevalence of ketonuria was significantly higher than that of ketonemia (x(2)=21.33, p <0.001). Significantly higher mean 3HB levels were observed with respect to ketonuria severity (p=0.001). Bedtime carbohydrate intake was associated with significantly lower 3HB levels (p=0.035). Insulin treatment was associated with significant 3HB levels reduction (p=0.032). Body weight reduction per week between two serial visits was associated with increased 3HB levels (p=0.005). Multiple linear regression analysis showed that weight loss remained the only independent predictor of 3HB levels. The presence of ketonemia was significantly lower than the presence of ketonuria. Weight loss per week was the only independent factor found to be associated with increased levels of 3HB. The clinical significance of this small increase requires further investigation.