A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans.

OBJECTIVES: The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. MATERIALS AND METHODS: The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion. RESULTS: AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95. CONCLUSIONS: A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.

Treatment of alcohol dependence. Alcohol and homelessness: social point of view.

The phenomenon of homeless people is eliciting a devastating social impact with an estimated prevalence in the USA and in Europe between 5.6% and 13.9%. These persons have a poor quality of life, a limited or no social life. They are often unemployed or work only occasionally. They are at risk for problems with the law and often suffering from addiction to other drugs, psychiatric and other medical diseases. Alcohol is often not the cause of their social status, but only the result of other discomforts thus contributing to their bio-psycho-social degradation. In 2009 the US Department of Housing and Urban Development's Homelessness Assistance Programs and in 2010 the European Consensus Conference on Homelessness discussed about the social rehabilitation of these people, using the concept of case management. In particular, the Standard Case Management was able to improve the housing stability, to reduce the use of drugs and to remove the working barriers. The Assertive Community Treatment was able to improve the housing stability and had a better efficacy for patients suffering from double diagnosis.

Drafting a dual diagnosis program: a tailored intervention for patients with complex clinical needs

Background: Clinical practice of mental health services changed in 1978 after the Basaglia Law was passed, and it is now characterized by usually voluntary treatments offered by community-based services. That broadened the interventions' focus from the single subject to their environment. Dual diagnosis is defined by WHO as «the co-occurrence in the same individual of a psychoactive substance use disorder and another psychiatric disorder¼. It is considered to be a "border territory" since entails networking between different medical services. Materials and methods: A literature search was performed in PubMed, Web of Science, Scopus and Google Scholar. Search terms were: "guidelines", "treatment", "comorbidity", "substance abuse", "alcohol", "dual-diagnosis", "psychiatric illness", "outpatient", "inpatient", "health care service", "clinical practice". National and regional regulations about health and addiction were screened too. Out of 598 titles, 31 studies were included in this article for their relevance on treatments and networking between services for dual diagnosis cases. Results: There are not any guidelines for clinical practice in the literature, neither there are any shared treatment strategies on a national level. Considering the autonomy that every regional health service has, several different courses of action are possible. Here there are reported the ones available. Conclusions: After discussing the weak points of the treatment options, we suggest the "Multidisciplinary Healthcare" model to best address the difficulties represented by dual diagnosis cases.