Machine Learning Model to Predict Diagnosis of Mild Cognitive Impairment by Using Radiomic and Amyloid Brain PET.

PURPOSE: The study aimed to develop a deep learning model for predicting amnestic mild cognitive impairment (aMCI) diagnosis using radiomic features and amyloid brain PET. PATIENTS AND METHODS: Subjects (n = 328) from the Alzheimer's Disease Neuroimaging Initiative database and the EudraCT 2015-001184-39 trial (159 males, 169 females), with a mean age of 72 ± 7.4 years, underwent PET/CT with 18 F-florbetaben. The study cohort consisted of normal controls (n = 149) and subjects with aMCI (n = 179). Thirteen gray-level run-length matrix radiomic features and amyloid loads were extracted from 27 cortical brain areas. The least absolute shrinkage and selection operator regression was used to select features with the highest predictive value. A feed-forward neural multilayer network was trained, validated, and tested on 70%, 15%, and 15% of the sample, respectively. Accuracy, precision, F1-score, and area under the curve were used to assess model performance. SUV performance in predicting the diagnosis of aMCI was also assessed and compared with that obtained from the machine learning model. RESULTS: The machine learning model achieved an area under the receiver operating characteristic curve of 90% (95% confidence interval, 89.4-90.4) on the test set, with 80% and 78% for accuracy and F1-score, respectively. The deep learning model outperformed SUV performance (area under the curve, 71%; 95% confidence interval, 69.7-71.4; 57% accuracy, 48% F1-score). CONCLUSIONS: Using radiomic and amyloid PET load, the machine learning model identified MCI subjects with 84% specificity at 81% sensitivity. These findings show that a deep learning algorithm based on radiomic data and amyloid load obtained from brain PET images improves the prediction of MCI diagnosis compared with SUV alone.

Breakthrough SARS-CoV-2 infections after COVID-19 mRNA vaccination in MS patients on disease modifying therapies during the Delta and the Omicron waves in Italy.

BACKGROUND: In this study we aimed to monitor the risk of breakthrough SARS-CoV-2 infection in patients with MS (pwMS) under different DMTs and to identify correlates of reduced protection. METHODS: This is a prospective Italian multicenter cohort study, long-term clinical follow-up of the CovaXiMS (Covid-19 vaccine in Multiple Sclerosis) study. 1855 pwMS scheduled for SARS-CoV-2 mRNA vaccination were enrolled and followed up to a mean time of 10 months. The cumulative incidence of breakthrough Covid-19 cases in pwMS was calculated before and after December 2021, to separate the Delta from the Omicron waves and to account for the advent of the third vaccine dose. FINDINGS: 1705 pwMS received 2 m-RNA vaccine doses, 21/28 days apart. Of them, 1508 (88.5%) had blood assessment 4 weeks after the second vaccine dose and 1154/1266 (92%) received the third dose after a mean interval of 210 days (range 90-342 days) after the second dose. During follow-up, 131 breakthrough Covid-19 infections (33 during the Delta and 98 during the Omicron wave) were observed. The probability to be infected during the Delta wave was associated with SARS-CoV-2 antibody levels measured after 4 weeks from the second vaccine dose (HR=0.57, p < 0.001); the protective role of antibodies was preserved over the whole follow up (HR=0.57, 95%CI=0.43-0.75, p < 0.001), with a significant reduction (HR=1.40, 95%CI=1.01-1.94, p=0.04) for the Omicron cases. The third dose significantly reduced the risk of infection (HR=0.44, 95%CI=0.21-0.90,p=0.025) during the Omicron wave. INTERPRETATION: The risk of breakthrough SARS-CoV-2 infections is mainly associated with reduced levels of the virus-specific humoral immune response. FUNDING: Supported by FISM - Fondazione Italiana Sclerosi Multipla - cod. 2021/Special-Multi/001 and financed or co-financed with the '5 per mille' public funding.

Effect of SARS-CoV-2 mRNA vaccination in MS patients treated with disease modifying therapies.

BACKGROUND: In patients with Multiple Sclerosis (pwMS) disease-modifying therapies (DMTs) affects immune response to antigens. Therefore, post-vaccination serological assessments are needed to evaluate the effect of the vaccine on SARS-CoV-2 antibody response. METHODS: We designed a prospective multicenter cohort study enrolling pwMS who were scheduled for SARS-Cov-2 vaccination with mRNA vaccines (BNT162b2, Pfizer/BioNTech,Inc or mRNA-1273, Moderna Tx,Inc). A blood collection before the first vaccine dose and 4 weeks after the second dose was planned, with a centralized serological assessment (electrochemiluminescence immunoassay, ECLIA, Roche-Diagnostics). The log-transform of the antibody levels was analyzed by multivariable linear regression. FINDINGS: 780 pwMS (76% BNT162b2 and 24% mRNA-1273) had pre- and 4-week post-vaccination blood assessments. 87 (11·2%) were untreated, 154 (19·7%) on ocrelizumab, 25 (3·2%) on rituximab, 85 (10·9%) on fingolimod, 25 (3·2%) on cladribine and 404 (51·7%) on other DMTs. 677 patients (86·8%) had detectable post-vaccination SARS-CoV-2 antibodies. At multivariable analysis, the antibody levels of patients on ocrelizumab (201-fold decrease (95%CI=128-317), p < 0·001), fingolimod (26-fold decrease (95%CI=16-42), p < 0·001) and rituximab (20-fold decrease (95%CI=10-43), p < 0·001) were significantly reduced as compared to untreated patients. Vaccination with mRNA-1273 resulted in a systematically 3·25-fold higher antibody level (95%CI=2·46-4·27) than with the BNT162b2 vaccine (p < 0·001). The antibody levels on anti-CD20 therapies correlated to the time since last infusion, and rituximab had longer intervals (mean=386 days) than ocrelizumab patients (mean=129 days). INTERPRETATION: In pwMS, anti-CD20 treatment and fingolimod led to a reduced humoral response to mRNA-based SARS-CoV-2 vaccines. As mRNA-1273 elicits 3·25-higher antibody levels than BNT162b2, this vaccine may be preferentially considered for patients under anti-CD20 treatment or fingolimod. Combining our data with those on the cellular immune response to vaccines, and including clinical follow-up, will contribute to better define the most appropriate SARS-CoV-2 vaccine strategies in the context of DMTs and MS. FUNDING: FISM[2021/Special-Multi/001]; Italian Ministry of Health'Progetto Z844A 5 × 1000'.

Abnormal sweating and "skin flushing" as possible predictive factor for treatment related fluctuations in Guillain-Barré syndrome: a case series and a review of the literature.

Treatment related fluctuations (TRFs) in Guillain-Barré Syndrome (GBS) are described as one or more episodes of deterioration manifesting within two months after disease onset and following an initial improvement or stabilisation after treatment. They may be encountered in 8% to 16% of patients, but currently predictive factors of TRF occurrence and severity are poorly known. To this end, we evaluated the frequency and clinical features of TRFs in a cohort of GBS patients admitted to the Neurological unit of Sant'Andrea Hospital (La Spezia, Italy) from January 1st, 2003 to December 31st, 2017. Among the 98 GBS collected patients, five (5.1%) developed a TRF during disease course. Consistently with the literature, the majority of our GBS patients who developed a TRF did not report a preceding diarrhoea, had a predominant proximal weakness and all of them had sensory disturbances at the clinical onset. Interestingly, 80% of our TRF patients manifested since GBS onset an autonomic dysfunction with abnormal sweating and a peculiar 'skin flushing' in face, neck and chest. Two patients developed respiratory insufficiency at the TRF time, and they both died. We would advise to pay attention to GBS patients with particular 'skin flushing' in face, neck and chest and abnormal sweating, because these findings could be a red flag for TRF.

Importance of intensive and prolonged rehabilitative treatment on the Guillain-Barrè syndrome long-term outcome: a retrospective study.

BACKGROUND: Guillain-Barrè syndrome (GBS) is often associated with a residual disability. Nonetheless, poor and incomplete studies have been published addressed towards the assessment of importance of physiotherapy (FKT) in the recovery. The aim of the study was to explore the effects of prolonged FKT associated with medical therapy and to evaluate the long-term outcome. METHODS: A retrospective analysis was carried out on patients with GBS who needed to continue rehabilitation after hospitalization and admitted to the Neurological Department of La Spezia from 2003 to 2017. MRC and GBS-Disability scale (GBS-DS) were performed at the time of greatest clinical disability, after medical therapy, and at the end of the overall FKT. The final outcome evaluation was based on the ability to walk with or without support. ANOVA with Bonferroni post-test were used to compare MRC and GBS-DS. RESULTS: Ninety-six patients were admitted, but only 51 satisfied inclusion criteria. Forty patients performed intensive treatment for an average of 60.95 days, and 31 of them, once discharged, are required to continue FKT as outpatients for a mean period of 96.45 days. The mean value of MRC and GBS-DS post-FKT improved significantly compared with the post-medical therapy. Concerning walking, among the 40 patients who did not walk before therapy, 8 need support after the medical therapy and 4 (11.76%) cannot walk independently at the last follow-up. CONCLUSIONS: In conclusion, FKT associated to medical therapy can improve the outcome of the disease, if performed for periods exceeding 6 months.

Are basketball players more likely to develop Hirayama disease?

Hirayama disease is a rare neurological disease affecting primarily men in the second to third decades. To date there are only few reports from Italy. We report the case of three young basketball players who presented with clinical, electrophysiological and MRI findings suggestive for Hirayama disease. Although the pathophysiology of the disease is still unknown, several hypotheses have been suggested and two of these are the disproportionate growth of cervical spine and cervical cord/roots during adolescence and the chronic traumatism. We think that, in our cases, the height of basketball players combined with the constant stress caused by the sport, could have contributed to the development of the Hirayama disease. With this report we would stress the importance to be careful to consider this pathology in order to avoid misdiagnosis predictive of poor prognosis in young patients.

Amyloid burden identifies neuropsychological phenotypes at increased risk of progression to Alzheimer's disease in mild cognitive impairment patients.

PURPOSE: The extent of amyloid burden associated with cognitive impairment in amnestic mild cognitive impairment is unknown. The primary aim of the study was to determine the extent to which amyloid burden is associated to the cognitive impairment. The secondary objective was to test the relationship between amyloid accumulation and memory or cognitive impairment. MATERIALS AND METHODS: In this prospective study 66 participants with amnestic mild cognitive impairment underwent clinical, neuropsychological and PET amyloid imaging tests. Composite scores assessing memory and non-memory domains were used to identify two clinical classes of neuropsychological phenotypes expressing different degree of cognitive impairment. Detection of amyloid status and definition of optimal amyloid ± cutoff for discrimination relied on unsupervised k-means clustering method. RESULTS: Threshold for identifying low and high amyloid retention groups was of SUVr = 1.3. Aß + participants showed poorer global cognitive and episodic memory performance than subjects with low amyloid deposition. Aß positivity significantly identified individuals with episodic memory impairment with a sensitivity and specificity of 80 and 79%, (χ2 = 21.48; P < 0.00001). Positive and negative predictive values were 82 and 76%, respectively. Amyloid deposition increased linearly as function of memory impairment with a rate of 0.13/ point of composite memory score (R = -44, P = 0.0003). CONCLUSION: The amyloid burden of SUVr = 1.3 allows early identification of subjects with episodic memory impairment which might predict progression from MCI to Alzheimer's disease. TRIAL REGISTRATION: EudraCT 2015-001184-39.

Increased incidence of axonal Guillain-Barré syndrome in La Spezia area of Italy: A 13-year follow-up study.

Guillain-Barré syndrome (GBS) is an acute immune-mediated polyradiculoneuropathy with a worldwide incidence of 0.81-1.89 per 100 000 person-years. In Europe and North America only 5% of patients with GBS have axonal subtypes, which in South America and Asia account for 30%-47% of cases. The aim of our study is to assess the annual incidence and clinical features of GBS in La Spezia area in Italy. A retrospective (from 1 January 2003 to 31 December 2011) followed by a prospective (from 1 January 2012 to 31 December 2015) analysis was carried out on patients admitted to La Spezia hospital who fulfilled the GBS diagnostic criteria. A total of 86 patients (58 men), mean age of 62.7 years (range 21-90), were included. The mean annual incidence rate was 3/100 000 (range: 0.9/100 000-5.37/100 000) significantly higher than the European incidence (P < 0.001). Forty-seven percent were classified as acute inflammatory demyelinating polyradiculoneuropathy (AIDP), 35% as acute motor and motor-sensory axonal neuropathy (AMAN-AMSAN), 13% as variant forms, and 5% were not defined. AIDP was most common in "Golfo dei Poeti" (50%) and "Val di Magra" (63.2%), whereas AMAN/AMSAN prevailed in "Val di Vara" (63.6%) and "Riviera Spezzina" (62.5%) (P = 0.024). In La Spezia area GBS incidence (especially the AMAN subtype) is significantly higher than the incidence reported in Europe. AIDP predominates in the eastern area whereas AMAN/AMSAN in the western, with a significantly different incidence rate (P = 0.003). Prospective studies to assess possible predisposing environmental factors are needed.

Molecular Imaging of Huntington's Disease.

The onset and the clinical progression of Huntington Disease (HD) is influenced by several events prompted by a genetic mutation that affects several organs tissues including different regions of the brain. In the last decades years, Positron Emission Tomography (PET) and Magnetic Resonance Imaging (MRI) helped to deepen the knowledge of neurodegenerative mechanisms that guide to clinical symptoms. Brain imaging with PET represents a tool to investigate the physiopathology occurring in the brain and it has been used to predict the age of onset of the disease and to evaluate the therapeutic efficacy of new drugs. This article reviews the contribution of PET and MRI in the research field on Huntington's disease, focusing in particular on some most relevant achievements that have helped recognize the molecular changes, the clinical symptoms and evolution of the disease. J. Cell. Physiol. 232: 1988-1993, 2017. © 2016 Wiley Periodicals, Inc.