Paving the Way for Predicting the Progression of Cognitive Decline: The Potential Role of Machine Learning Algorithms in the Clinical Management of Neurodegenerative Disorders.

Alzheimer's disease (AD) is the most common form of neurodegenerative disorder. The prodromal phase of AD is mild cognitive impairment (MCI). The capacity to predict the transitional phase from MCI to AD represents a challenge for the scientific community. The adoption of artificial intelligence (AI) is useful for diagnostic, predictive analysis starting from the clinical epidemiology of neurodegenerative disorders. We propose a Machine Learning Model (MLM) where the algorithms were trained on a set of neuropsychological, neurophysiological, and clinical data to predict the diagnosis of cognitive decline in both MCI and AD patients. METHODS: We built a dataset with clinical and neuropsychological data of 4848 patients, of which 2156 had a diagnosis of AD, and 2684 of MCI, for the Machine Learning Model, and 60 patients were enrolled for the test dataset. We trained an ML algorithm using RoboMate software based on the training dataset, and then calculated its accuracy using the test dataset. RESULTS: The Receiver Operating Characteristic (ROC) analysis revealed that diagnostic accuracy was 86%, with an appropriate cutoff value of 1.5; sensitivity was 72%; and specificity reached a value of 91% for clinical data prediction with MMSE. CONCLUSION: This method may support clinicians to provide a second opinion concerning high prognostic power in the progression of cognitive impairment. The MLM used in this study is based on big data that were confirmed in enrolled patients and given a credibility about the presence of determinant risk factors also supported by a cognitive test score.

Policy-Based Holistic Application Management with BPMN and TOSCA.

With the wide adoption of cloud computing across technology industries and research institutions, an ever-growing interest in cloud orchestration frameworks has emerged over the past few years. These orchestration frameworks enable the automated provisioning and decommissioning of cloud applications in a timely and efficient manner, but they offer limited or no support for application management. While management functionalities, such as configuring, monitoring and scaling single components, can be directly covered by cloud providers and configuration management tools, holistic management features, such as backing up, testing and updating multiple components, cannot be automated using these approaches. In this paper, we propose a concept to automatically generate executable holistic management workflows based on the TOSCA standard. The practical feasibility of the approach is validated through a prototype implementation and a case study.

COLLABORADI: a rule-based diagnostic imaging prescription system to help the general practitioner to choose the most appropriate radiological imaging procedures.

Significant advances in medical imaging have been made in the past decades, enabling physicians to reach high precision in diagnosing patients' diseases by means of sophisticated imaging tools. However, the use of sophisticated tools is limited by the high costs and, in some cases, by the utilization of ionizing radiation, which have both great impact on the economy of a nation and on citizens' health, respectively. Guidelines have been published among countries to provide physicians with structured rules to be followed to suggest the correct imaging technique, suiting better the diagnostic question and avoiding inappropriate imaging requests. The COLLABORADI is a research project that addressed the phenomenon of inappropriate imaging prescriptions in Sicily (Italy) and proposed the design and implementation of a clinical decision support system to help physicians to set up the most appropriate diagnostic route for their patients. The aim of this paper is to describe the characteristics of the COLLABORADI software and its potential impact in diminishing inappropriate imaging.

To treat or not to treat: comparison of different criteria used to determine whether weight loss is to be recommended.

BACKGROUND: Excess body fat is a major risk factor for disease primarily due to its endocrine activity. In recent years several criteria have been introduced to evaluate this factor. Nevertheless, treatment need is currently assessed only on the basis of an individual's Body Mass Index (BMI), calculated as body weight (in kg) divided by height in m2. The aim of our study was to determine whether application of the BMI, compared to adiposity-based criteria, results in underestimation of the number of subjects needing lifestyle intervention. METHODS: We compared treatment need based on BMI classification with four adiposity-based criteria: percentage body fat (%BF), considered both alone and in relation to metabolic syndrome risk (MS), waist circumference (WC), as an index of abdominal fat, and Body Fat Mass Index (BFMI, calculated as fat mass in kg divided by height in m2) in 63 volunteers (23 men and 40 women, aged 20 - 65 years). RESULTS: According to the classification based on BMI, 6.3% of subjects were underweight, 52.4% were normal weight, 30.2% were overweight, and 11.1% were obese. Agreement between the BMI categories and the other classification criteria categories varied; the most notable discrepancy emerged in the underweight and overweight categories. BMI compared to almost all of the other adiposity-based criteria, identified a lower percentage of subjects for whom treatment would be recommended. In particular, the proportion of subjects for whom clinicians would strongly recommend weight loss on the basis of their BMI (11.1%) was significantly lower than those identified according to WC (25.4%, p = 0.004), %BF (28.6%, p = 0.003), and MS (33.9%, p = 0.002). CONCLUSION: The use of the BMI alone, as opposed to an assessment based on body composition, to identify individuals needing lifestyle intervention may lead to unfortunate misclassifications. Population-specific data on the relationships between body composition, morbidity, and mortality are needed to improve the diagnosis and treatment of at-risk individuals.

Patient dose during radiological examination in the follow-up of bariatric surgery.

A patient dose survey was carried out measuring the kerma-area product (KAP) values during radiological evaluation in the follow-up of bariatric surgery. The procedures were performed by three radiologists to adjust laparoscopic gastric bands and to detect postoperative complications after Roux-en-Y gastric bypass procedures to treat morbid obesity. Total fluoroscopy time, exposure factors and the overall contribution of fluoroscopy to the accumulated KAP value were recorded. The median KAP values were used to estimate organ doses and effective dose to a standard patient; the radiation risk associated with the procedures was also evaluated. The doses were smaller for one of the three radiologists, owing to a more appropriate beam collimation and a reduction of the screening time. The KAP values ranged from 1.6 to 7.1 Gy cm(2) for the laparoscopic adjustable gastric banding management, and from 3.0 and 8.3 Gy cm(2) for the radiological examinations after gastric bypass. As a whole, the effective doses associated to these procedures were between 0.5 and 2.7 mSv. The organs receiving the highest doses were not only breast, stomach, pancreas and liver, but also lungs, owing to of their high radiosensitivity, significantly contributed to the effective dose.