A machine learning approach for predicting high risk hospitalized patients with COVID-19 SARS-Cov-2.

BACKGROUND: This study aimed to explore whether explainable Artificial Intelligence methods can be fruitfully used to improve the medical management of patients suffering from complex diseases, and in particular to predict the death risk in hospitalized patients with SARS-Cov-2 based on admission data. METHODS: This work is based on an observational ambispective study that comprised patients older than 18 years with a positive SARS-Cov-2 diagnosis that were admitted to the hospital Azienda Ospedaliera "SS Antonio e Biagio e Cesare Arrigo", Alessandria, Italy from February, 24 2020 to May, 31 2021, and that completed the disease treatment inside this structure. The patients'medical history, demographic, epidemiologic and clinical data were collected from the electronic medical records system and paper based medical records, entered and managed by the Clinical Study Coordinators using the REDCap electronic data capture tool patient chart. The dataset was used to train and to evaluate predictive ML models. RESULTS: We overall trained, analysed and evaluated 19 predictive models (both supervised and unsupervised) on data from 824 patients described by 43 features. We focused our attention on models that provide an explanation that is understandable and directly usable by domain experts, and compared the results against other classical machine learning approaches. Among the former, JRIP showed the best performance in 10-fold cross validation, and the best average performance in a further validation test using a different patient dataset from the beginning of the third COVID-19 wave. Moreover, JRIP showed comparable performances with other approaches that do not provide a clear and/or understandable explanation. CONCLUSIONS: The ML supervised models showed to correctly discern between low-risk and high-risk patients, even when the medical disease context is complex and the list of features is limited to information available at admission time. Furthermore, the models demonstrated to reasonably perform on a dataset from the third COVID-19 wave that was not used in the training phase. Overall, these results are remarkable: (i) from a medical point of view, these models evaluate good predictions despite the possible differences entitled with different care protocols and the possible influence of other viral variants (i.e. delta variant); (ii) from the organizational point of view, they could be used to optimize the management of health-care path at the admission time.

Translation, cross-cultural adaptation, reliability, and validation of the italian version of the Foot and Ankle Disability Index (FADI).

BACKGROUND AND AIM OF THE WORK: Foot-and-Ankle-Disability-Index (FADI) is one of the most widely used evaluation questionnaires for this anatomical district, but an italian validated version lacks and is necessary to properly evaluate italian people. In fact a correct interpretation of the items by patients is essential to obtain a precise subjective response, making the questionnaire valid to evaluate patients' satisfaction and wellness. Our purpose was to translate and culturally adapt into Italian the FADI questionnaire, and to check its reproducibility and validity. MATERIALS AND METHODS: The original english version of FADI questionnaire was translated into Italian and checked for medical part coherence. It was submitted to 10 italian randomized patients to verify a correct cultural adaptation, and then to other 50 randomized patients operated at their ankle or hallux to assess intra- and inter-observer reproducibility by the Pearson's-Correlation-Coefficient (PCC) and the Intra-Class-Correlation (ICC) coefficient. Moreover, Short-Form-36 (SF36) questionnaire for Quality-of-Life and Visual-Analogue-Scale (VAS) for pain were also administered to the same 60 people and compared to italian-FADI to perform validation analysis by PCC and ICC coefficient. RESULTS: Cultural adaptation of the translated version of the scale resulted good in terms of understandability by patients. An optimal correlation of the inter- and intra-observer reproducibility was obtained. The correlation obtained between FADI and SF-36 as well as between FADI and VAS indicates success in the validation process. CONCLUSIONS: Validation of the FADI italian version has been performed successfully, its use can be considered appropriate and is indicated in italian clinical practice. (www.actabiomedica.it).

Translation, cross-cultural adaptation, reliability, and validation of the Italian version of the American Orthopaedic Foot and Ankle Society - MetaTarsoPhalangeal-InterPhalangeal Scale (AOFAS-MTP-IP) for the hallux.

BACKGROUND AND AIM OF THE WORK: An incorrect interpretation or patients' misunderstanding of evaluation scales can induce a mistake; therefore the real applicability of an evaluation scale should be determined by procedures that take care of cultural adaptability and not only of scientific validity. Our purpose was to translate and culturally adapt into Italian the AOFAS-MTP-IP scale for hallux, and to check its reproducibility and validity. METHODS: The AOFAS-MTP-IP scale was processed for translation and checked for medical part coherence. The scale was submitted to 10 patients to verify a correct cultural adaptation. Then, the scale was submitted to 50 randomized patients operated at their hallux. Intra and inter-observer reproducibility was checked by two interviewers and a repeated interview. Short-Form-36-questionnaire for Quality of Life and Visual-Analogue-Scale for pain were also administered to perform validation analysis. The Pearson's-Correlation-Coefficient and the Intra-Class-Correlation coefficient were calculated to analyse the scale reproducibility and validation. RESULTS: Cultural adaptation of the translated version of the scale resulted good in terms of understandability by patients. An optimal correlation of the inter and intra-observer reproducibility was obtained. The correlation with well-known validated scales as SF-36 and VAS has shown good correlation indicating success in the validation process. CONCLUSIONS: Validation of the Italian version of the AOFAS-MTP-IP evaluation scale for hallux has been performed successfully. Therefore its use can be considered appropriate and suggested in Italian clinical practice.