Long-term pulmonary sequelae in COVID-19 patients are currently under investigation worldwide. Potential relationships between blood sampling and functional and radiological findings are crucial to guide the follow-up. In this study, we collected and evaluated clinical status, namely symptoms and patients’ reported outcome, pulmonary function tests (PFT), laboratory tests, and radiological findings at 3- and 12-months post-discharge in patients admitted between 25 February and 2 May 2020, and who survived severe COVID-19 pneumonia. A history of chronic pulmonary disease or COVID-19-unrelated complications were used as exclusion criteria. Unenhanced CTs were analyzed quantitatively (compromising lung volume %) and qualitatively, with main patterns of: ground-glass opacity (GGO), consolidation, and reticular configuration. Patients were subsequently divided into groups based on their radiological trends and according to the evolution in the percentage of compromised lung volume. At 12 months post-discharge, seventy-one patients showed significantly improved laboratory tests and PFT. Among them, 63 patients also underwent CT examination: all patients with negative CT findings at three months (n = 14) had negative CT also at 12 months; among the 49/63 patients presenting CT alterations at three months, 1/49 (2%) normalized, 40/49 (82%) improved, 7/49 (14%) remained stably abnormal, and 1/49 (2%) worsened. D-dimer values were low in patients with normal CT and higher in cases with improved or stably abnormal CT (median values 213 vs. 329 vs. 1000 ng/mL, respectively). The overall compromised lung volume was reduced compared with three months post-discharge (12.3 vs. 14.4%, p < 0.001). In stably abnormal CT, the main pulmonary pattern changed, showing a reduction in GGO and an increase in reticular configuration. To summarize, PFT are normal in most COVID-19 survivors 12 months post-discharge, but CT structural abnormalities persist (although sensibly improved over time) and are associated with higher D-dimer values.
PI-RADS 3 prostate lesions clinical management is still debated, with high variability among different centers. Identifying clinically significant tumors among PI-RADS 3 is crucial. Radiomics applied to multiparametric MR (mpMR) seems promising. Nevertheless, reproducibility assessment by external validation is required. We retrospectively included all patients with at least one PI-RADS 3 lesion (PI-RADS v2.1) detected on a 3T prostate MRI scan at our Institution (June 2016–March 2021). An MRI-targeted biopsy was used as ground truth. We assessed reproducible mpMRI radiomic features found in the literature. Then, we proposed a new model combining PSA density and two radiomic features (texture regularity (T2) and size zone heterogeneity (ADC)). All models were trained/assessed through 100-repetitions 5-fold cross-validation. Eighty patients were included (26 with GS ≥ 7). In total, 9/20 T2 features (Hector’s model) and 1 T2 feature (Jin’s model) significantly correlated to biopsy on our dataset. PSA density alone predicted clinically significant tumors (sensitivity: 66%; specificity: 71%). Our model obtained a sensitivity of 80% and a specificity of 76%. Standard-compliant works with detailed methodologies achieve comparable radiomic feature sets. Therefore, efforts to facilitate reproducibility are needed, while complex models and imaging protocols seem not, since our model combining PSA density and two radiomic features from routinely performed sequences appeared to differentiate clinically significant cancers.
Hepatocellular carcinoma (HCC) is the fifth most common cancer worldwide and the third most common cause of cancer-related death. Cirrhosis is a major contributing factor, accounting for over 90% of HCC cases. With the high mortality rate of HCC, earlier detection of HCC is critical. When added to magnetic resonance imaging (MRI), artificial intelligence (AI) has been shown to improve HCC detection. Nonetheless, to date no cost-effectiveness analyses have been conducted on an AI tool to enhance earlier HCC detection. This study reports on the cost-effectiveness of detection of liver lesions with AI improved MRI in the surveillance for HCC in patients with a cirrhotic liver compared to usual care (UC). The model structure included a decision tree followed by a state-transition Markov model from an Italian healthcare perspective. Lifetime costs and quality-adjusted life years (QALY) were simulated in cirrhotic patients at risk of HCC. One-way sensitivity analyses and two-way sensitivity analyses were performed. Results were presented as incremental cost-effectiveness ratios (ICER). For patients receiving UC, the average lifetime costs per 1,000 patients were €16,604,800 compared to €16,610,250 for patients receiving the AI approach. With a QALY gained of 0.55 and incremental costs of €5,000 for every 1,000 patients, the ICER was €9,888 per QALY gained, indicating cost-effectiveness with the willingness-to-pay threshold of €33,000/QALY gained. Main drivers of cost-effectiveness included the cost and performance (sensitivity and specificity) of the AI tool. This study suggests that an AI-based approach to earlier detect HCC in cirrhotic patients can be cost-effective. By incorporating cost-effective AI-based approaches in clinical practice, patient outcomes and healthcare efficiency are improved.
Objectives: To support the cognitive model of Freezing of Gait (FoG) we investigated FoG in a cohort of patients with Dementia with Lewy Bodies (DLB).Materials and Methods: We assessed FoG frequency in 19 DLB patients compared to 19 control PD patients within 2 years from symptom onset and with at least 5 years follow‐up. The two groups were matched by age and motor presentation at onset, severity of parkinsonism and disease duration. The presence and severity of FoG was identified as those with a score of 1 or greater on subitem 14 of the Unified Parkinson's Disease Rating Scale Part II (UPDRS II).Results: At T0, 68.4% DLB and 10.5% PD patients experienced FoG ≥1. The prevalence of FoG increased with disease progression (94.7% DLB and 47.3% PD subjects had FoG ≥1 at T5). DLB also showed a more severe FoG (FoG ≥2) than PD (21% vs. 0% at T0 and 52.6% vs. 10.5% at T5), consistently with previous studies reporting FoG prevalence in DLB.Conclusion: This is the first study looking specifically at FoG in DLB, identifying it as a frequent and early feature of DLB and emphasizing the crucial role of cognitive impairment in the occurrence of this mysterious phenomenon.