Directional Relationship Between Vitamin D Status and Prediabetes: A New Approach from Artificial Neural Network in a Cohort of Workers with Overweight-Obesity.

Objective: Despite the increasing literature on the association of diabetes with inflammation, cardiovascular risk, and vitamin D (25(OH)D) concentrations, strong evidence on the direction of causality among these factors is still lacking. This gap could be addressed by means of artificial neural networks (ANN) analysis.Methods: Retrospective observational study was carried out by means of an innovative data mining analysis-known as auto-contractive map (AutoCM)-and semantic mapping followed by Activation and Competition System on data of workers referring to an occupational-health outpatient clinic. Parameters analyzed included weight, height, waist circumference, body mass index (BMI), percentage of fat mass, glucose, insulin, glycated hemoglobin (HbA1c), creatinine, total cholesterol, low- and high-density lipoprotein cholesterol, triglycerides, uric acid, fibrinogen, homocysteine, C-reactive protein (CRP), diastolic and systolic blood pressure, and 25(OH)D.Results: The study included 309 workers. Of these, 23.6% were overweight, 40.5% were classified into the first class of obesity, 23.3% were in the second class, and 12.6% were in the third class (BMI > 40 kg/m ). All mean biochemical values were in normal range, except for total cholesterol, low- and high-density lipoprotein cholesterol, CRP, and 25(OH)D. HbA1c was between 39 and 46 mmol/mol in 51.78%. 25(OH)D levels were sufficient in only 12.6%. Highest inverse correlation for hyperglycemia onset was with BMI and waist circumference, suggesting a protective role of 25(OH)D against their increase. AutoCM processing and the semantic map evidenced direct association of 25(OH)D with high link strength (0.99) to low CRP levels and low high-density lipoprotein cholesterol levels. Low 25(OH)D led to changes in glucose, which affected metabolic syndrome biomarkers, first of which was homeostatic model assessment index and blood glucose, but not 25(OH)D.Conclusions: The use of ANN suggests a key role of 25(OH)D respect to all considered metabolic parameters in the development of diabetes and evidences a causation between low 25(OH)D and high glucose concentrations.

Determinants of metabolic syndrome in obese workers: gender differences in perceived job-related stress and in psychological characteristics identified using artificial neural networks.

OBJECTIVE: The metabolic syndrome (MS) is a multifactorial disorder associated with a higher risk of developing cardiovascular diseases and type 2 diabetes. However, its pathophysiology and risk factors are still poorly understood. In this study, we investigated the associations among gender, psychosocial variables, job-related stress and the presence of MS in a cohort of obese Caucasian workers. METHODS: A total of 210 outpatients (142 women, 68 men) from an occupational medicine service was enrolled in the study. Age, BMI, waist circumference, fasting glucose, blood pressure, triglycerides and HDL cholesterol were collected to define MS. In addition, we evaluated eating behaviors, depressive symptoms, and work-related stress. Data analyses were performed with an artificial neural network algorithm called Auto Semantic Connectivity Map (AutoCM), using all available variables. RESULTS: MS was diagnosed in 54.4 and 33.1% of the men and women, respectively. AutoCM evidenced gender-specific clusters associated with the presence or absence of MS. Men with a moderate occupational physical activity, obesity, older age and higher levels of decision-making freedom at work were more likely to have a diagnosis of MS than women. Women with lower levels of decision-making freedom, and higher levels of psychological demands and social support at work had a lower incidence of MS but showed higher levels of binge eating and depressive symptomatology. CONCLUSION: We found a complex gender-related association between MS, psychosocial risk factors and occupational determinants. The use of these information in surveillance workplace programs might prevent the onset of MS and decrease the chance of negative long-term outcomes. LEVEL OF EVIDENCE: Level V, observational study.

Endometrial preparation with Dienogest before hysteroscopic surgery: a systematic review.

PURPOSE: Hysteroscopic surgery is considered the gold standard for the minimal invasive treatment of many endouterine diseases such as endometrial polyps or submucous myomas. Recently, many studies have evaluated the effect of preoperative administration of a number of drugs to reduce endometrial thickness and achieve important intraoperative advantages. The purpose of this systematic review is to summarize the available evidence about the use of Dienogest, an orally administrable progestin, for endometrial preparation before hysteroscopic surgery. METHODS: All studies published on this topic and indexed on PubMed/MEDLINE, Embase or Google scholar databases were retrieved and analysed. RESULTS: We retrieved five studies about this topic. Considered together, the published data analyses allow us to conclude that Dienogest is effective in reducing the thickness of the endometrium, the severity of bleeding and also of operative time, with a lower number of side effects compared with other pharmacological preparations or no treatment. CONCLUSION: Administration of Dienogest may be an effective and safe treatment for endometrial thinning before operative hysteroscopy. However, this conclusion is based on few reports and further studies to prove or disprove it are warranted.

Digging deeper on "deep" learning: A computational ecology approach.

We propose an alternative approach to "deep" learning that is based on computational ecologies of structurally diverse artificial neural networks, and on dynamic associative memory responses to stimuli. Rather than focusing on massive computation of many different examples of a single situation, we opt for model-based learning and adaptive flexibility. Cross-fertilization of learning processes across multiple domains is the fundamental feature of human intelligence that must inform "new" artificial intelligence.

Pleiotropic Actions of Peroxisome Proliferator-Activated Receptors (PPARs) in Dysregulated Metabolic Homeostasis, Inflammation and Cancer: Current Evidence and Future Perspectives.

BACKGROUND: Peroxisome proliferator-activated receptors (PPARs) have demonstrated a lot of important effects in the regulation of glucose and lipid metabolism and in the correct functioning of adipose tissue. Recently, many studies have evaluated a possible effect of PPARs on tumor cells. The purpose of this review is to describe the effects of PPARs, their action and their future prospective; METHODS: Narrative review aimed to synthesize cutting-edge evidence retrieved from searches of computerized databases; RESULTS: PPARs play a key role in metabolic diseases, which include several cardiovascular diseases, insulin resistance, type 2 diabetes, metabolic syndrome, impaired immunity and the increasing risk of cancer; in particular, PPARα and PPARß/δ mainly enable energy combustion, while PPARγ contributes to energy storage by enhancing adipogenesis; CONCLUSION: PPAR agonists could represent interesting types of molecules that can treat not only metabolic diseases, but also inflammation and cancer. Additional research is needed for the identification of high-affinity, high-specificity agonists for the treatment of obesity, type 2 diabetes (T2DM) and other metabolic diseases. Further studies are needed also to elucidate the role of PPARs in cancer.

Efficacy of real-time continuous glucose monitoring on glycaemic control and glucose variability in type 1 diabetic patients treated with either insulin pumps or multiple insulin injection therapy: a randomized controlled crossover trial.

BACKGROUND: The aim of this study was to determine the efficacy of real-time continuous glucose monitoring in T1D patients treated with insulin pump therapy or multiple daily insulin therapy. METHODS: Twenty adult patients (ten insulin pump therapy and ten multiple daily insulin) with poor glycaemic control (HbA1c > 8.0%) were randomized into two groups for 6 months: the continuous glucose monitoring arm (using real-time continuous glucose monitoring) and the SMBG arm. After 2 months of wash-out, the participants crossed over. The primary outcome was HbA1c reduction. The secondary outcomes were hypoglycaemia and hyperglycaemia risk assessment (area under the curve < 70 mg/dL/day and AUC > 200 mg/dL/day, respectively) and glucose variability. RESULTS: Fourteen patients (eight multiple daily insulin, six insulin pump therapy) used continuous glucose monitoring appropriately (at least 40% of the time). In these patients, the improvement in glycaemic control was more evident during the real-time continuous glucose monitoring period (7.76% ± 0.4 vs 8.54% ± 0.4, p < 0.05) than during the self-monitoring of blood glucose period (8.42% ± 0.4 vs 8.56% ± 0.5, p = 0.2). Better results with continuous glucose monitoring were observed in patients using multiple daily insulin with greater improvement in both glycaemic control (7.71% ± 0.2 vs 8.58% ± 0.2, p < 0.05) and glucose variability and with a marked reduction in the risk of both hypoglycaemia and hyperglycaemia. CONCLUSIONS: Appropriate use of real-time continuous glucose monitoring improved glycometabolic control in T1D patients. The effects of continuous glucose monitoring were more evident in patients under multiple daily insulin treatment, compared with insulin pump therapy. Glucose variability, in addition to glycaemic control, was improved in compliant diabetic patients.

Why Mathematical Computer Simulations Are the New Laboratory for Scientists.

In this paper, we introduce a new powerful scientific paradigm to understand natural and cultural processes. This new paradigm is based on two fundamental keywords: Data, as representative sample of the process we need to analyze, and Artificial Adaptive Systems, as a new mathematical technique able to make explicit the nonlinearity embedded in the process. We will try to make explicit these concepts analyzing how the distribution of events into the physical space may reveal the hidden logic connecting these events together.

Innovative diagnostic tools for early detection of Alzheimer's disease.

Current state-of-the-art diagnostic measures of Alzheimer's disease (AD) are invasive (cerebrospinal fluid analysis), expensive (neuroimaging) and time-consuming (neuropsychological assessment) and thus have limited accessibility as frontline screening and diagnostic tools for AD. Thus, there is an increasing need for additional noninvasive and/or cost-effective tools, allowing identification of subjects in the preclinical or early clinical stages of AD who could be suitable for further cognitive evaluation and dementia diagnostics. Implementation of such tests may facilitate early and potentially more effective therapeutic and preventative strategies for AD. Before applying them in clinical practice, these tools should be examined in ongoing large clinical trials. This review will summarize and highlight the most promising screening tools including neuropsychometric, clinical, blood, and neurophysiological tests.

Similarity coefficients for binary chemoinformatics data: overview and extended comparison using simulated and real data sets.

This paper reports an analysis and comparison of the use of 51 different similarity coefficients for computing the similarities between binary fingerprints for both simulated and real chemical data sets. Five pairs and a triplet of coefficients were found to yield identical similarity values, leading to the elimination of seven of the coefficients. The remaining 44 coefficients were then compared in two ways: by their theoretical characteristics using simple descriptive statistics, correlation analysis, multidimensional scaling, Hasse diagrams, and the recently described atemporal target diffusion model; and by their effectiveness for similarity-based virtual screening using MDDR, WOMBAT, and MUV data. The comparisons demonstrate the general utility of the well-known Tanimoto method but also suggest other coefficients that may be worthy of further attention.

Artificial neural networks accurately predict mortality in patients with nonvariceal upper GI bleeding.

BACKGROUND: Risk stratification systems that accurately identify patients with a high risk for bleeding through the use of clinical predictors of mortality before endoscopic examination are needed. Computerized (artificial) neural networks (ANNs) are adaptive tools that may improve prognostication. OBJECTIVE: To assess the capability of an ANN to predict mortality in patients with nonvariceal upper GI bleeding and compare the predictive performance of the ANN with that of the Rockall score. DESIGN: Prospective, multicenter study. SETTING: Academic and community hospitals. PATIENTS: This study involved 2380 patients with nonvariceal upper GI bleeding. INTERVENTION: Upper GI endoscopy. MAIN OUTCOME MEASUREMENTS: The primary outcome variable was 30-day mortality, defined as any death occurring within 30 days of the index bleeding episode. Other outcome variables were recurrent bleeding and need for surgery. RESULTS: We performed analysis of certified outcomes of 2380 patients with nonvariceal upper GI bleeding. The Rockall score was compared with a supervised ANN (TWIST system, Semeion), adopting the same result validation protocol with random allocation of the sample in training and testing subsets and subsequent crossover. Overall, death occurred in 112 cases (4.70%). Of 68 pre-endoscopic input variables, 17 were selected and used by the ANN versus 16 included in the Rockall score. The sensitivity of the ANN-based model was 83.8% (76.7-90.8) versus 71.4% (62.8-80.0) for the Rockall score. Specificity was 97.5 (96.8-98.2) and 52.0 (49.8 4.2), respectively. Accuracy was 96.8% (96.0-97.5) versus 52.9% (50.8-55.0) (P<.001). The predictive performance of the ANN-based model for prediction of mortality was significantly superior to that of the complete Rockall score (area under the curve 0.95 [0.92-0.98] vs 0.67 [0.65-0.69]; P<.001). LIMITATIONS: External validation on a subsequent independent population is needed, patients with variceal bleeding and obscure GI hemorrhage are excluded. CONCLUSION: In patients with nonvariceal upper GI bleeding, ANNs are significantly superior to the Rockall score in predicting the risk of death.

Detection of an Autism EEG Signature From Only Two EEG Channels Through Features Extraction and Advanced Machine Learning Analysis.

BACKGROUND AND OBJECTIVE: In 2 previous studies, we have shown the ability of special machine learning systems applied to standard EEG data in distinguishing children with autism spectrum disorder (ASD) from non-ASD children with an overall accuracy rate of 100% and 98.4%, respectively. Since the equipment routinely available in neonatology units employ few derivations, we were curious to check if just 2 derivations were enough to allow good performance in the same cases of the above-mentioned studies. METHODS: A continuous segment of artifact-free EEG data lasting 1 minute in ASCCI format from C3 and C4 EEG channels present in 2 previous studies, was used for features extraction and subsequent analyses with advanced machine learning systems. A features extraction software package (Python tsfresh) applied to time-series raw data derived 1588 quantitative features. A special hybrid system called TWIST (Training with Input Selection and Testing), coupling an evolutionary algorithm named Gen-D and a backpropagation neural network, was used to subdivide the data set into training and testing sets as well as to select features yielding the maximum amount of information after a first variable selection performed with linear correlation index threshold. RESULTS: After this intelligent preprocessing, 12 features were extracted from C3-C4 time-series of study 1 and 36 C3-C4 time-series of study 2 representing the EEG signature. Acting on these features the overall accuracy predictive capability of the best artificial neural network acting as a classifier in deciphering autistic cases from typicals (study 1) and other neuropsychiatric disorders (study 2) resulted in 100 % for study 1 and 94.95 % for study 2. CONCLUSIONS: The results of this study suggest that also a minor part of EEG contains precious information useful to detect autism if treated with advanced computational algorithms. This could allow in the future to use standard EEG from newborns to check if the ASD signature is already present at birth.

Analysis of COVID-19 pandemic in USA, using Topological Weighted Centroid.

The first case of COVID-19 in USA was reported on January 20, 2020. The number of COVID-19 confirmed cases and death has increased since the first reported case and the outbreak has appeared in all states. This paper analyzes disease outbreak using Topological Weighted Centroid (TWC), which is a data driven intelligent geographical dynamical system that models disease spread in space and time. In this analysis the COVID-19 cases in USA on March 26, 2020 as provided by Johns Hopkins University is used. The COVID-19 outbreak is mapped by the TWC method. We were able to predict and capture some features of the pandemic spread using the early data. Although we have used the geographical distance from the latitude and longitude coordinates, our results indicate that one of the main paths of diseases spread are arguably airline routes. In this analysis, we used a large set of data. A modified version of TWC, is named TWC-Windowing to elaborate the effect of data from all places.

Assessment of New Coronary Features on Quantitative Coronary Angiographic Images With Innovative Unsupervised Artificial Adaptive Systems: A Proof-of-Concept Study.

Background and Purpose: The Active Connection Matrixes (ACMs) are unsupervised artificial adaptive systems able to extract from digital images features of interest (edges, tissue differentiation, etc.) unnoticeable with conventional systems. In this proof-of-concept study, we assessed the potentiality of ACMs to increase measurement precision of morphological structures (e.g., stenosis and lumen diameter) and to grasp morphological features (arterial walls) from quantitative coronary angiography (QCA), unnoticeable on the original images. Methods: Archive images of QCA and intravascular ultrasound (IVUS) of 10 patients (8 men, age 69.1 ± 9.7 years) who underwent both procedures for clinical reasons were retrospectively analyzed. Arterial features derived from "IVUS images," "conventional QCA images," and "ACM-reprocessed QCA images" were measured in 21 coronary segments. Portions of 1-mm length (263 for lumen and 526 for arterial walls) were head-to-head compared to assess quali-quantitative between-methods agreement. Results: When stenosis was calculated on "ACM-reprocessed QCA images," the bias vs. IVUS (gold standard) did not improve, but the correlation coefficient of the QCA-IVUS relationship increased from 0.47 to 0.83. When IVUS-derived lumen diameters were compared with diameters obtained on ACM-reprocessed QCA images, the bias (-0.25 mm) was significantly smaller (p < 0.01) than that observed with original QCA images (0.58 mm). ACMs were also able to extract arterial wall features from QCA. The bias between the measures of arterial walls obtained with IVUS and ACMs, although significant (p < 0.01), was small [0.09 mm, 95% CI (0.03, 0.14)] and the correlation was fairly good (r = 0.63; p < 0.0001). Conclusions: This study provides proof of concept that ACMs increase the measurement precision of coronary lumen diameter and allow extracting from QCA images hidden features that mirror well the arterial walls derived by IVUS.

Appropriateness guidelines and predictive rules to select patients for upper endoscopy: a nationwide multicenter study.

OBJECTIVES: Selecting patients appropriately for upper endoscopy (EGD) is crucial for efficient use of endoscopy. The objective of this study was to compare different clinical strategies and statistical methods to select patients for EGD, namely appropriateness guidelines, age and/or alarm features, and multivariate and artificial neural network (ANN) models. METHODS: A nationwide, multicenter, prospective study was undertaken in which consecutive patients referred for EGD during a 1-month period were enrolled. Before EGD, the endoscopist assessed referral appropriateness according to the American Society for Gastrointestinal Endoscopy (ASGE) guidelines, also collecting clinical and demographic variables. Outcomes of the study were detection of relevant findings and new diagnosis of malignancy at EGD. The accuracy of the following clinical strategies and predictive rules was compared: (i) ASGE appropriateness guidelines (indicated vs. not indicated), (ii) simplified rule (>or=45 years or alarm features vs. <45 years without alarm features), (iii) logistic regression model, and (iv) ANN models. RESULTS: A total of 8,252 patients were enrolled in 57 centers. Overall, 3,803 (46%) relevant findings and 132 (1.6%) new malignancies were detected. Sensitivity, specificity, and area under the receiver-operating characteristic curve (AUC) of the simplified rule were similar to that of the ASGE guidelines for both relevant findings (82%/26%/0.55 vs. 88%/27%/0.52) and cancer (97%/22%/0.58 vs. 98%/20%/0.58). Both logistic regression and ANN models seemed to be substantially more accurate in predicting new cases of malignancy, with an AUC of 0.82 and 0.87, respectively. CONCLUSIONS: A simple predictive rule based on age and alarm features is similarly effective to the more complex ASGE guidelines in selecting patients for EGD. Regression and ANN models may be useful in identifying a relatively small subgroup of patients at higher risk of cancer.

Multi factorial interactions in the pathogenesis pathway of Alzheimer's disease: a new risk charts for prevention of dementia.

BACKGROUND: The population longitudinal study named "The Conselice Study" has been the focus of the present investigation. 65 years old or older participants of this population study on brain aging were followed up for 5 years: 937 subjects completed the follow-up. Relationships of 46 genetic, phenotypic, clinical and nutritional factors on incident cognitive decline and incident dementia cases were investigated. RESULTS: A new statistical approach, called the Auto Contractive Map (AutoCM) was applied to find relationship between variables and a possible hierarchy in the relevance of each variable with incident dementia. This method, based on an artificial adaptive system, was able to define the association strength of each variable with all the others. Moreover, few variables resulted to be aggregation points in the variable connectivity map related to cognitive decline and dementia. Gene variants and cognate phenotypic variables showed differential degrees of relevance to brain aging and dementia. A risk map for age associated cognitive decline and dementia has been constructed and will be presented and discussed. CONCLUSION: This map of variables may be use to identify subjects with increased risk of developing cognitive decline end/or dementia and provide pivotal information for early intervention protocols for prevention of dementia.

A machine learning approach for differentiating malignant from benign enhancing foci on breast MRI.

BACKGROUND: Differentiate malignant from benign enhancing foci on breast magnetic resonance imaging (MRI) through radiomic signature. METHODS: Forty-five enhancing foci in 45 patients were included in this retrospective study, with needle biopsy or imaging follow-up serving as a reference standard. There were 12 malignant and 33 benign lesions. Eight benign lesions confirmed by over 5-year negative follow-up and 15 malignant histopathologically confirmed lesions were added to the dataset to provide reference cases to the machine learning analysis. All MRI examinations were performed with a 1.5-T scanner. One three-dimensional T1-weighted unenhanced sequence was acquired, followed by four dynamic sequences after intravenous injection of 0.1 mmol/kg of gadobenate dimeglumine. Enhancing foci were segmented by an expert breast radiologist, over 200 radiomic features were extracted, and an evolutionary machine learning method ("training with input selection and testing") was applied. For each classifier, sensitivity, specificity and accuracy were calculated as point estimates and 95% confidence intervals (CIs). RESULTS: A k-nearest neighbour classifier based on 35 selected features was identified as the best performing machine learning approach. Considering both the 45 enhancing foci and the 23 additional cases, this classifier showed a sensitivity of 27/27 (100%, 95% CI 87-100%), a specificity of 37/41 (90%, 95% CI 77-97%), and an accuracy of 64/68 (94%, 95% CI 86-98%). CONCLUSION: This preliminary study showed the feasibility of a radiomic approach for the characterisation of enhancing foci on breast MRI.

Geographical identification of Chianti red wine based on ICP-MS element composition.

Chianti is a precious red wine and enjoys a high reputation for its high quality in the world wine market. Despite this, the production region is small and product needs efficient tools to protect its brands and prevent adulterations. In this sense, ICP-MS combined with chemometrics has demonstrated its usefulness in food authentication. In this study, Chianti/Chianti Classico, authentic wines from vineyard of Toscana region (Italy), together samples from 18 different geographical regions, were analyzed with the objective of differentiate them from other Italian wines. Partial Least Squares-Discriminant Analysis (PLS-DA) identified variables to discriminate wine geographical origin. Rare Earth Elements (REE), major and trace elements all contributed to the discrimination of Chianti samples. General model was not suited to distinguish PDO red wines from samples, with similar chemical fingerprints, collected in some regions. Specific classification models enhanced the capability of discrimination, emphasizing the discriminant role of some elements.

Combined use of sonographic and elastosonographic parameters can improve the diagnostic accuracy in thyroid nodules at risk of malignancy at cytological examination.

BACKGROUND: Thyroid nodules diagnosed as Thy3B at fine-needle aspiration biopsy have a relevant risk of malignancy (15-30%) and are usually addressed to surgery. However surgery will result unnecessary in most cases. The present study aims at evaluating the possible increase of diagnostic accuracy for predicting malignancy using novel sonographic and elastographic parameters. METHODS: In fifty patients undergoing thyroidectomy because of a Thy3B thyroid nodule, sonographic and elastosonographic evaluation was carried out by single operator before surgery. Five sonographic parameters (echogenicity, irregular margins, microcalcifications, intra-nodule blood flow and its irregularity) and two elastosonographic parameters (intra-nodule stiffness and its extension to adjacent tissue) were considered. After obtaining histological diagnosis, diagnostic accuracy was calculated. RESULTS: When the two procedures were analyzed separately, sensitivity, specificity, positive (PPV) and negative (NPV) predictive values were 100%, 85%, 63% and 100% for ultrasonography and 60%, 92.5%, 67%, 90% for elastrosonography, respectively. The newly introduced evaluation procedures increased sensitivity. When a combined sonographic and elastosonographic evaluation was introduced, diagnostic accuracy was significantly improved: when ≥4 out of the seven parameters indicated were present, the risk of malignancy was very high (sensitivity 100%, specificity 92.55%, PPV 77%, NPV 100%). CONCLUSIONS: A novel combined sonographic and elastosonographic parameter evaluation improved diagnostic accuracy for identifying thyroid nodules suspicious of malignancy.

Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data.

BACKGROUND: Reverse Transcription-Polymerase Chain Reaction (RT-PCR) for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) diagnosis currently requires quite a long time span. A quicker and more efficient diagnostic tool in emergency departments could improve management during this global crisis. Our main goal was assessing the accuracy of artificial intelligence in predicting the results of RT-PCR for SARS-COV-2, using basic information at hand in all emergency departments. METHODS: This is a retrospective study carried out between February 22, 2020 and March 16, 2020 in one of the main hospitals in Milan, Italy. We screened for eligibility all patients admitted with influenza-like symptoms tested for SARS-COV-2. Patients under 12 years old and patients in whom the leukocyte formula was not performed in the ED were excluded. Input data through artificial intelligence were made up of a combination of clinical, radiological and routine laboratory data upon hospital admission. Different Machine Learning algorithms available on WEKA data mining software and on Semeion Research Centre depository were trained using both the Training and Testing and the K-fold cross-validation protocol. RESULTS: Among 199 patients subject to study (median [interquartile range] age 65 [46-78] years; 127 [63.8%] men), 124 [62.3%] resulted positive to SARS-COV-2. The best Machine Learning System reached an accuracy of 91.4% with 94.1% sensitivity and 88.7% specificity. CONCLUSION: Our study suggests that properly trained artificial intelligence algorithms may be able to predict correct results in RT-PCR for SARS-COV-2, using basic clinical data. If confirmed, on a larger-scale study, this approach could have important clinical and organizational implications.

The "MS-ROM/IFAST" Model, a Novel Parallel Nonlinear EEG Analysis Technique, Distinguishes ASD Subjects From Children Affected With Other Neuropsychiatric Disorders With High Degree of Accuracy.

Background and Objective. In a previous study, we showed a new EEG processing methodology called Multi-Scale Ranked Organizing Map/Implicit Function As Squashing Time (MS-ROM/IFAST) performing an almost perfect distinction between computerized EEG of Italian children with autism spectrum disorder (ASD) and typically developing children. In this study, we assessed this system in distinguishing ASD subjects from children affected with other neuropsychiatric disorders (NPD). Methods. At a psychiatric practice in Texas, 20 children diagnosed with ASD and 20 children diagnosed with NPD were entered into the study. Continuous segments of artifact-free EEG data lasting 10 minutes were entered in MS-ROM/IFAST. From the new variables created by MS-ROM/IFAST, only 12 has been selected according to a correlation criterion. The selected features represent the input on which supervised machine learning systems (MLS) acted as blind classifiers. Results. The overall predictive capability in distinguishing ASD from other NPD cases ranged from 93% to 97.5%. The results were confirmed in further experiments in which Italian and US data have been combined. In this analysis, the best MLS reached 95.0% global accuracy in 1 out of 3 classes distinction (ASD, NPD, controls). This study demonstrates the value of EEG processing with advanced MLS in the differential diagnosis between ASD and NPD cases. The results were not affected by age, ethnicity and technicalities of EEG acquisition, confirming the existence of a specific EEG signature in ASD cases. To further support these findings, it was decided to test the behavior of already trained neural networks on 10 Italian very young ASD children (25-37 months). In this test, 9 out of 10 cases have been correctly recognized as ASD subjects in the best case. Conclusions. These results confirm the possibility of an early automatic autism detection based on standard EEG.