How primary care research can be improved in clinical practice? An Italian case study.

BACKGROUND: Primary care is considered essential for the sustainability of the Health System. Practice-Based Research Networks (PBRN) play a strategic role in translation of primary care research into practice. Research Capacity Building in primary care requires a improvement and development strategy and well-developed research infrastructures to support physicians. METHODS: We used the system development methodology referring to the Lean Thinking to create and support a research team in primary and pediatric care. In particular a "cascade" deployment model and the X-Matrix, a framework used in management studies to support strategy definition and management process. RESULTS: A research unit in primary and pediatric care has been created, by sharing vision, mission, core values, long-term strategies. The definition of a annual planning led to monitoring actions to guarantee the expected goals. CONCLUSIONS: Lean methodology is useful to adapt to various managerial and operational contexts, including healthcare. In our case it allowed team members to spread the culture of research, its importance and role to improve the health of patients, thank to the organizational support of a hospital IR, the Research and Innovation Department.

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.

Baseline clinical characteristics and prognostic factors in hospitalized COVID-19 patients aged ≤ 65 years: A retrospective observational study.

BACKGROUND: Individual differences in susceptibility to SARS-CoV-2 infection, symptomatology and clinical manifestation of COVID-19 have thus far been observed but little is known about the prognostic factors of young patients. METHODS: A retrospective observational study was conducted on 171 patients aged ≤ 65 years hospitalized in Alessandria's Hospital from 1st March to 30th April 2020 with laboratory confirmed COVID-19. Epidemiological data, symptoms at onset, clinical manifestations, Charlson Comorbidity Index, laboratory parameters, radiological findings and complications were considered. Patients were divided into two groups on the basis of COVID-19 severity. Multivariable logistic regression analysis was used to establish factors associated with the development of a moderate or severe disease. FINDINGS: A total of 171 patients (89 with mild/moderate disease, 82 with severe/critical disease), of which 61% males and a mean age (± SD) of 53.6 (± 9.7) were included. The multivariable logistic model identified age (50-65 vs 18-49; OR = 3.23 CI95% 1.42-7.37), platelet count (per 100 units of increase OR = 0.61 CI95% 0.42-0.89), c-reactive protein (CPR) (per unit of increase OR = 1.12 CI95% 1.06-1.20) as risk factors for severe or critical disease. The multivariable logistic model showed a good discriminating capacity with a C-index value of 0.76. INTERPRETATION: Patients aged ≥ 50 years with low platelet count and high CRP are more likely to develop severe or critical illness. These findings might contribute to improved clinical management.