Automatic Speech Classifier for Mild Cognitive Impairment and Early Dementia

The World Health Organization estimates that 50 million people are currently living with dementia worldwide and this figure will almost triple by 2050. Current pharmacological treatments are only symptomatic, and drugs or other therapies are ineffective in slowing down or curing the neurodegenerative process at the basis of dementia. Therefore, early detection of cognitive decline is of the utmost importance to respond significantly and deliver preventive interventions. Recently, the researchers showed that speech alterations might be one of the earliest signs of cognitive defect, observable well in advance before other cognitive deficits become manifest. In this article, we propose a full automated method able to classify the audio file of the subjects according to the progress level of the pathology. In particular, we trained a specific type of artificial neural network, called autoencoder, using the visual representation of the audio signal of the subjects, that is, the spectrogram. Moreover, we used a data augmentation approach to overcome the problem of the large amount of annotated data usually required during the training phase, which represents one of the most major obstacles in deep learning. We evaluated the proposed method using a dataset of 288 audio files from 96 subjects: 48 healthy controls and 48 cognitively impaired participants. The proposed method obtained good classification results compared to the state-of-the-art neuropsychological screening tests and, with an accuracy of 90.57%, outperformed the methods based on manual transcription and annotation of speech.

Are Oropharyngeal Dysphagia Screening Tests Effective in Preventing Pneumonia?

Oropharyngeal dysphagia, a clinical condition that indicates difficulty in moving food and liquid from the oral cavity to the esophagus, has a markedly high prevalence in the elderly. The number of elderly people with oropharyngeal dysphagia is expected to increase due to the aging of the world’s population. Understanding the current situation of dysphagia screening is crucial when considering future countermeasures. We report findings from a literature review including citations on current objective dysphagia screening tests: the Water Swallowing Test, Mann Assessment of Swallowing Ability, and the Gugging Swallowing Screen. Pneumonia can be predicted using the results of the screening tests discussed in this review, and the response after the screening tests is important for prevention. In addition, although interdisciplinary team approaches prevent and reduce aspiration, optimal treatment is a challenging. Intervention studies with multiple factors focusing on the elderly are needed.

Multi-Parametric Magnetic Resonance Imaging-Based Radiomics Analysis of Cervical Cancer for Preoperative Prediction of Lymphovascular Space Invasion

BackgroundDetection of lymphovascular space invasion (LVSI) in early cervical cancer (CC) is challenging. To date, no standard clinical markers or screening tests have been used to detect LVSI preoperatively. Therefore, non-invasive risk stratification tools are highly desirable.ObjectiveTo train and validate a multi-parametric magnetic resonance imaging (mpMRI)-based radiomics model to detect LVSI in patients with CC and investigate its potential as a complementary tool to enhance the efficiency of risk assessment strategies.Materials and MethodsThe model was developed from the tumor volume of interest (VOI) of 125 patients with CC. A total of 1037 radiomics features obtained from conventional magnetic resonance imaging (MRI), including a small field-of-view (sFOV) high-resolution (HR)-T2-weighted MRI (T2WI), apparent diffusion coefficient (ADC), T2WI, fat-suppressed (FS)-T2WI, as well as axial and sagittal contrast-enhanced T1-weighted MRI (T1c). We conducted a radiomics-based characterization of each tumor region using pretreatment image data. Feature selection was performed using the least absolute shrinkage and selection operator method on the training set. The predictive performance was compared with single variates (clinical data and single-layer radiomics signatures) analyzed using a receiver operating characteristic (ROC) curve. Three-fold cross-validation performed 20 times was used to evaluate the accuracy of the trained classifiers and the stability of the selected features. The models were validated by using a validation set.ResultsFeature selection extracted the six most important features (3 from sFOV HR-T2WI, 1 T2WI, 1 FS-T2WI, and 1 T1c) for model construction. The mpMRI-combined radiomics model (area under the curve [AUC]: 0.940) reached a significantly higher performance (better than the clinical parameters [AUC: 0.730]), including any single-layer model using sFOV HR-T2WI (AUC: 0.840), T2WI (AUC: 0.770), FS-T2WI (AUC: 0.710), ADC maps (AUC: 0.650), sagittal, and axial T1c values (AUC: 0.710, 0.680) in the validation set.ConclusionBiomarkers using multi-parametric radiomics features derived from preoperative MR images could predict LVSI in patients with CC.

Financial Incapacity of Patients with Mild Alzheimer’s Disease: What Neurologists Need to Know about Where the Impairment Lies

Research in the last decade has focused on assessing financial capacity and incapacity mainly in old age, but new research has turned to address the question of how financial incapacity can be predicted by cognitive factors. The aim of this study was to identify which cognitive domains predict financial capacity and the relevant cognitive skills of patients with mild Alzheimer’s disease (AD) in order to assist neurologists in functional assessment and further patient referral. In this study, 109 patients diagnosed with mild AD were examined with a number of neuropsychological tests: Mini-Mental State Examination (MMSE), Functional Rating Scale for Symptoms of Dementia (FRSSD), Functional Cognitive Assessment Scale (FUCAS), Trail Making Test (TMT)-Part B, Rey-Osterrieth Complex Figure Test (ROCFT)-copy condition and delayed recall condition, Rey Auditory Verbal Learning Test (RAVLT), Boston Naming Test, Rivermead Behavioural Memory Test (RBMT), digit span forward and backward, WAIS-R digit symbol substitution test, Neuropsychiatric Inventory (NPI), Geriatric Depression Scale (GDS-15), and the Legal Capacity for Property Law Transactions Assessment Scale (LCPLTAS). LCPLTAS total score and relevant subdomains were best predicted only by the score of one item coming from MMSE: subtraction of serial sevens. This is the only measure of arithmetic testing in use for the Greek geriatric population. Financial capacity is severely impaired in the group of mild AD patients. In order to prevent financial exploitation cases, neurologists, neuropsychologists, psychiatrists, and geriatrists should pay close attention to the information from the relevant arithmetic question of MMSE, as it is one of the most widely administered screening tests in clinical settings.

MEN1 Surveillance Guidelines: Time to (re)Think?

Clinical Practice Guidelines for patients with Multiple Endocrine Neoplasia type 1 (MEN1) recommend a variety of surveillance options. Given progress over the past decade in this area, it is timely to evaluate their ongoing utility. MEN1 is characterized by the development of synchronous or asynchronous tumors affecting a multitude of endocrine and non-endocrine tissues, resulting in premature morbidity and mortality, such that the rationale for undertaking surveillance screening in at-risk individuals appears robust. Current guidelines recommend an intensive regimen of clinical, biochemical and radiological surveillance commencing in early childhood for those with a clinical or genetic diagnosis of MEN1, with the aim of early tumor detection and treatment. Although it is tempting to assume that such screening results in patient benefits and improved outcomes, the lack of a strong evidence base for several aspects of MEN1 care, and the potential for iatrogenic harms related to screening tests or interventions of unproven benefit, make such assumptions potentially unsound. Furthermore, the psychological, as well as economic burdens of intensive screening remain largely unstudied. Although screening undoubtedly constitutes an important component of MEN1 patient care, this perspective aims to highlight some of the current uncertainties and challenges related to existing MEN1 guidelines with a particular focus on the role of screening for pre-symptomatic tumors. Looking forward, a screening approach that acknowledges these limitations and uncertainties and places the patient at the heart of the decision-making process, is advocated.

Concurrent Hearing and Genetic Screening among Newborns in Ningbo, China

Objective. To detect the carrier rates of deafness gene variants in populations in Ningbo and analyze the risk of hereditary hearing loss through concurrent hearing and genetic screening tests. Methods. Two thousand one hundred and seventy-four newborns were enrolled from November 2018 to August 2019. All subjects underwent hearing screening and newborn deafness genetic screening with 15 variants in 4 genes, and the positive sites were simultaneously verified by sequencing. Results. The total carrier rate of genetic variants in Ningbo reached 4.32%, when GJB2 c.235delC was the variant with the highest prevalence (2.12%), approximately accounting for 48.9% of the total carrier frequency. The carrier frequency of SLC26A4 c.919-2A>G was 0.87%, while the most common variant in mitochondrial DNA (mtDNA) MT-RNR1 gene was m.1555A>G, and its carrier frequency was 0.184%. In the OAE testing, 92 newborns passing hearing screening were tested positively for variants in 4 genes, and 2 of 42 newborns who failed in the first hearing test were found to mutate in 4 genes. Conclusion. Herein, the results concerning the carrier rates for deafness gene mutations of Ningbo population are reported. Our study is beneficial to the insight into the deafness genomic epidemiology for deafness genes in Ningbo population and provides the reference for healthcare in Ningbo.

Structural and Functional Characterization of Four Novel Fibrinogen Mutations in FGB Causing Congenital Fibrinogen Disorder

Congenital fibrinogen disorders are caused by mutations in genes coding for fibrinogen and may lead to various clinical phenotypes. Here, we present a functional and structural analysis of 4 novel variants located in the FGB gene coding for fibrinogen Bβ chain-heterozygous missense BβY416C and BβA68S, homozygous nonsense BβY345*, and heterozygous nonsense BβW403* mutations. The cases were identified by coagulation screening tests and further investigated by various methods. Fibrin polymerization had abnormal development with decreased maximal absorbance in all patients. Plasmin-induced fibrin degradation revealed different lytic phases of BβY416C and BβW403* than those of the control. Fibrinopeptide cleavage measured by reverse phase high pressure liquid chromatography of BβA68S showed impaired release of fibrinopeptide B. Morphological properties, studied through scanning electron microscopy, differed significantly in the fiber thickness of BβY416C, BβA68S, and BβW403*, and in the fiber density of BβY416C and BβW403*. Finally, homology modeling of BβA68S showed that mutation caused negligible alternations in the protein structure. In conclusion, all mutations altered the correct fibrinogen function or structure that led to congenital fibrinogen disorders.