Diabetic retinopathy screening with confocal fundus camera and artificial intelligence - assisted grading.

PURPOSE: Screening for diabetic retinopathy (DR) by ophthalmologists is costly and labour-intensive. Artificial Intelligence (AI) for automated DR detection could be a clinically and economically alternative. We assessed the performance of a confocal fundus imaging system (DRSplus, Centervue SpA), coupled with an AI algorithm (RetCAD, Thirona B.V.) in a real-world setting. METHODS: 45° non-mydriatic retinal images from 506 patients with diabetes were graded both by an ophthalmologist and by the AI algorithm, according to the International Clinical Diabetic Retinopathy severity scale. Less than moderate retinopathy (DR scores 0, 1) was defined as non-referable, while more severe stages were defined as referable retinopathy. The gradings were then compared both at eye-level and patient-level. Key metrics included sensitivity, specificity all measured with a 95% Confidence Interval. RESULTS: The percentage of ungradable eyes according to the AI was 2.58%. The performances of the AI algorithm for detecting referable DR were 97.18% sensitivity, 93.73% specificity at eye-level and 98.70% sensitivity and 91.06% specificity at patient-level. CONCLUSIONS: DRSplus paired with RetCAD represents a reliable DR screening solution in a real-world setting. The high sensitivity of the system ensures that almost all patients requiring medical attention for DR are referred to an ophthalmologist for further evaluation.

Feasibility and accuracy of the screening for diabetic retinopathy using a fundus camera and an artificial intelligence pre-evaluation application.

AIMS: Periodical screening for diabetic retinopathy (DR) by an ophthalmologist is expensive and demanding. Automated DR image evaluation with Artificial Intelligence tools may represent a clinical and cost-effective alternative for the detection of retinopathy. We aimed to evaluate the accuracy and reliability of a machine learning algorithm. METHODS: This was an observational diagnostic precision study that compared human grader classification with that of DAIRET®, an algorithm nested in an electronic medical record powered by Retmarker SA. Retinal images were taken from 637 consecutive patients attending a routine annual diabetic visit between June 2021 and February 2023. They were manually graded by an ophthalmologist following the International Clinical Diabetic Retinopathy Severity Scale and the results were compared with those of the AI responses. The main outcome measures were screening performance, such as sensitivity and specificity and diagnostic accuracy by 95% confidence intervals. RESULTS: The rate of cases classified as ungradable was 1.2%, a figure consistent with the literature. DAIRET® sensitivity in the detection of cases of referable DR (moderate and above, "sight-threatening" forms of retinopathy) was equal to 1 (100%). The specificity, that is the true negative rate of absence of DR, was 80 ± 0.04. CONCLUSIONS: DAIRET® achieved excellent sensitivity for referable retinopathy compared with that of human graders. This is undoubtedly the key finding of the study and translates into the certainty that no patient in need of the ophthalmologist is misdiagnosed as negative. It also had sufficient specificity to represent a cost-effective alternative to manual grade alone.

Healthcare-acquired infections in rehabilitation units of the Lombardy Region, Italy.

BACKGROUND: Little data are available on the frequency and risk factors for infection in patients in rehabilitation units. METHODS: This was a 2-year retrospective cohort study conducted in 131 rehabilitation units (RUs) of the Lombardy Region, including those for patients requiring musculoskeletal, cardiac, respiratory, neurological and general geriatric rehabilitation. RUs were stratified into three groups by infection rate calculated from administrative data, and a random sample of RUs in each group was selected for analysis. Discharges from these RUs were randomly selected for chart review, and healthcare-acquired infection was confirmed using CDC/NHSN definitions. A logistic regression analysis explored the association among demographic variables of age, sex, type of rehabilitation unit, Charlson comorbidity score, and location prior to RU admission for selected infections. RESULTS: For the 3,028 discharges from 28 RUs, hospital administrative data had a sensitivity of 0.45 and a positive predictive value of 0.89 to identify infections in the chart review. At least one infection occurred in 14.9% of patient discharges, with 71% of infections being urinary, 8.0% respiratory, and 5% skin and soft tissue. Urinary infection was associated with female sex [odds ratio (OR) 1.48, 95% confidence interval (CI) 1.13-1.93], age 75-85 years (OR 2.21, 95% CI 1.12-4.34), Charlson comorbidity score of ≥3 (OR 1.54, 95% CI 1.10-2.17), and the transfer from acute care (OR 1.45, 95% CI 1.04-2.02). For respiratory infection, male sex (OR 3.06, 95% CI 1.51-6.18), comorbidity score of 1 or 2 (OR 2.16, 95% CI 1.08-4.36), and transfer from a healthcare setting other than an acute care hospital were independent risks (OR 3.14, 95% CI 1.15-8.53). CONCLUSION: Infections are common in residents of these rehabilitation units, and risk factors may differ with type of infection. The proportion of infections which may be prevented and effective prevention strategies need to be determined.

Cognitive dysfunction in SLE: development of a screening tool.

BACKGROUND: Cognitive dysfunction (CD) is among the most common neuropsychiatric manifestations of systemic lupus erythematosus (SLE). There are two methods which have been used to detect CD in patients with SLE: traditional neuropsychological tests (NPT) and the Automated Neuropsychological Assessment Metrics (ANAM). Both are time-consuming and neither is readily available for screening purposes. PURPOSE: The aim of our study was to evaluate the Montreal Cognitive Assessment (MoCA) test as a screening tool for detection of CD in SLE. Methods. SLE patients fulfilling ACR criteria were administered the ANAM, a computerized test battery which measures various cognitive domains and the MoCA, a one-page, performance-based screening test designed to detect mild cognitive impairment in the elderly. With the ANAM as the gold standard, the performance characteristics of the MoCA were assessed. RESULTS: In total, 44 patients were evaluated. Of these, 11 (25%) were identified by the ANAM as being impaired in comparison with 13 (29.5%) by the MoCA. The scores were significantly correlated (r = 0.57, p < 0.001). Using the standard cutoff of 26, the sensitivity of MoCA was 83% and specificity 73%. CONCLUSION: The MoCA appears to be a promising screening tool for the detection of CD in SLE both for epidemiologic studies and for routine clinical care.

[Investigation of potential risk factors for Salmonella enterica subsp enterica serotype Napoli: a nested case-control study in Lombardia region]. / Identificazione di potenziali fattori di rischio per i casi di infezione da Salmonella enterica subsp enterica sierotipo Napoli attraverso uno studio caso-controllo nidificato con- dotto in Regione Lombardia.

Enter-net surveillance system has detected the re-emergence of Salmonella enterica subsp enterica serotype Napoli (S. Napoli) since 2002. Preliminary data show that food vehicle could not be the only one implicated in the transmission of this serotype. A nested case-control study has been conducted using data form a prospective cohort: for each salmonellosis notification in Lombardia from May 2004 to December 2005 an ad hoc epidemiological investigation has been performed. Cases have been defined as subjects affected by salmonellosis with a positive faecal sample for Salmonella serotype Napoli and controls as subjects affected by salmonellosis with a positive faecal sample for Salmonella serotype not Napoli. Among 2185 salmonellosis notifications collected by 12 of 15 Local Health Authorities, we identified 67 cases and 867 controls. Infection due to S. Napoli were significantly more common among subjects with exposure to surface water (adjusted Odds Ratio (OR) = 3,82; 95% Confidence Interval (C.I.)=1,03-14,19), to domestic animals (adjusted OR = 3,22; 95% C.I. = 1,28-8,10) and among person who practice activities connected to surface water (adjusted OR 3,88; 95% C.I.=1,15-13,05) compared to subjects not exposed to these factors. Hyperendemia of S. Napoli could be attributable to an animal reservoir not yet identified: surface water contamination may be a direct (waterborne infection) or indirect (foodborne infection) vehicle for transmission of S. Napoli. behaviour. Regarding the relations of the neuroendocrine parameters and driving behaviour, positive correlations were observed between dopamine levels and frequency of driving violations while a negative relationship was found between adrenaline levels and frequency of driving errors. In conclusion the identification of psycho-physiological variables related to driving risky behaviour might be a useful instrument to design traffic safety programs tailored to high risk subjects.

[Preadolescents' nutritional habits: a survey in the secondary schools in Brianza]. / Le abitudini alimentari dei preadolescenti: indagine nelle scuole medie della Brianza.

AIM: This study was aimed at assessing eating habits among preadolescents living in Brianza, with a special focus on snacking' and breakfast' habits. METHODS: The research was carried out in 12 post-primary schools in Brianza and included 802 students attending 43 different classes (49.3% males and 50.7% females; mean age:12.6 years). The research tool was an ad hoc questionnaire administered to the preadolescents attending school on the day of the research. Data were analyzed using program Epi Info 6. RESULTS: Many students (78.3%) had breakfast in the morning of the questionnaire's administration. Among those perceiving themselves as overweight, not having breakfast is more common than among others. This information is the opposite of what preadolescents say when inquired about their habit to have ''a good breakfast'': only 36.8% of the responders declare that it happens on a daily basis. As to snacking, 18.7% of the students declare to be used to having multiple snacking during the day; during school recess on the day of the survey, 39.9% of respondents declared that they had eaten various industrial snacks, while 27.4% had cakes or fresh bread, 1.2% both of them and 0.6% fruit. On a daily basis, 59.5% report to eat various and different fruits and 62.9% report the same when inquired about vegetables. CONCLUSION: Considering the importance of a correct nutrition during developmental age and the importance of the phase of adolescence in establishing permanent nutritional habits that will last life-long, it is thus an educational priority to help preadolescents to choose the best foods for their health and well being.

[Pre-adolescents and sport: results of a health survey in some secondary schools of Brianza]. / I preadolescenti e lo sport: risultati di un'indagine in alcune scuole medie dell'area brianzola.

This study is aimed at assessing time dedicated to, motivation and involvement in physical activity on behalf of pre-adolescents. 802 students (49.3% boys and 50.7% girls; mean age: 12.6) attending 43 classes of 11 Brianza's post-elementary schools. A questionnaire was prepared and administered to the involved sample. Classes took part in this study through randomized selection and data were analyzed using program Epi Info 6. Most of the respondents (60.1%) stay involved in sport because "it makes me feel good" and 32.4% because sport is "enjoyable and entertaining". Pre-adolescents chose the sport in which they become engaged on the basis of personal inclination (40%), in order to share experiences and their free time with friends (15.4%); 13.7% declare to prefer sport to be practiced in team. (13.7%). The most practiced sport are: football (51.3% boys, 4.5% girls), volley (3.9%-36.4%), dance (0.8%-25.2%) e swimming (9.4%-14%). 80.8% in the sample practice physical activity in settings outside schools and, among these, 51.7% dedicate three or more hours weekly to extra-school activities. There are significant differences (p < 0.05) between males' and females' engagement in physical activity (mean value: 4.1 hours; males: 4.6 h, females: 3.5 h). Among pre-teens, 18% declare to be physically inactive at all; 15.7% do not take part in sport activities because afraid to be bullied or shamed by peers. Research show that males are significantly more involved in physical activity than females.