A deep learning model for Alzheimer's disease diagnosis based on patient clinical records.

BACKGROUND: Dementia, with Alzheimer's disease (AD) being the most common type of this neurodegenerative disease, is an under-diagnosed health problem in older people. The creation of classification models based on AD risk factors using Deep Learning is a promising tool to minimize the impact of under-diagnosis. OBJECTIVE: To develop a Deep Learning model that uses clinical data from patients with dementia to classify whether they have AD. METHODS: A Deep Learning model to identify AD in clinical records is proposed. In addition, several rebalancing methods have been used to preprocess the dataset and several studies have been carried out to tune up the model. RESULTS: Model has been tested against other well-established machine learning techniques, having better results than these in terms of AUC with alpha less than 0.05. CONCLUSIONS: The developed Neural Network Model has a good performance and can be an accurate assisting tool for AD diagnosis.

Aging, depression and dementia: The inflammatory process.

Population aging that we are currently witnessing has led to an increase in chronic age-related diseases, with dementia and depression being highlighted. Several studies establish a relationship between dementia and depression, although without defining the mechanism that links them. Some studies establish depression as a prodrome of dementia, while others consider it a risk factor for dementia. One of the events that is common between dementia and depression is the inflammatory process. In depression, an increase in inflammatory cytokines has been described, which would justify the serotonergic, noradrenergic and dopaminergic dysfunction of depression. This increase entails altering the activity of the hypothalamic-pituitary-adrenal (HPA) axis, thus linking chronic stress to depression, and the consequent weakening of the blood-brain barrier (BBB), facilitating the passage of pro-inflammatory factors. In this line, recent studies suggest that inflammation could direct the development of the pathogenesis of dementia, particularly Alzheimer's disease (AD), once the pathology has begun. In addition, sustained exposure to pro-inflammatory cytokines characteristic of aging could alter the microglial function and the expression of enzymes responsible for amyloid peptide metabolism, aggravating the pathological process. In view of the involvement of the inflammatory process in both conditions, it is necessary to investigate the events which both conditions share, such as the inflammatory process, to know the involvement of the inflammatory process in both dementia and depression, possible relationship of these 2 conditions, and consequently, to establish the clinical approach to both conditions.

Spanish adaptation and validation of the Pain Assessment Scale in Advanced Dementia (PAINAD) in patients with dementia and impaired verbal communication: cross-sectional study.

OBJECTIVES: The aim of this study was to adapt and validate the Pain Assessment in Advanced Dementia (PAINAD) scale in Spanish. DESIGN: Cross-sectional observational study. SETTING: Two health districts of Andalusian provinces, located in the south of Spain, through the Andalusian network of Primary Healthcare centres and four institutions dedicated to the care of patients with dementia. PARTICIPANTS: A total of 100 older people, with a medical diagnosis of dementia and a score on the Global Deterioration Scale between 5 and 7 were assessed using the PAINAD scale. PRIMARY AND SECONDARY OUTCOME MEASURES: Psychometric properties including content validity, construct validity and reliability of the scale have been tested. RESULTS: The overall Item Content Validity Index was excellent (0.95). Regarding construct validity, it was confirmed that a lower use of analgesics implied a lower score on the PAINAD scale (p<0.05). The internal consistency of the scale was 0.76 and it increases to 0.81 if we remove the breathing item. Furthermore, the intraclass correlation coefficient (ICC) used to assess interobserver reliability was 0.94, whereas the ICC used to assess temporary stability was 0.55. CONCLUSIONS: The Spanish version of the PAINAD scale is a valid tool to assess pain in patients with dementia and inability to communicate verbally.

Correlation between Biomarkers of Pain in Saliva and PAINAD Scale in Elderly People with Cognitive Impairment and Inability to Communicate.

The pain assessment in advanced dementia (PAINAD) appears to be a clinically useful tool. However, the salivary determination of tumor necrosis factor receptor type II (sTNF-RII) and secretory IgA (sIgA) as pain biomarkers is still incipient. The aim was to correlate the PAINAD score with sTNF-RII and sIgA biomarker levels in the saliva of patients with advanced dementia. In this regard, a cross-sectional study was conducted. The sample consisted of 75 elderly patients with a clinical diagnosis of dementia and a global deterioration scale (GDS) score of 5 to 7. The PAINAD scale was determined by a previously trained professional and the collection of salivary samples was performed using the passive secretion method. Human sTNF-RII and sIgA using ELISA kits. The results showed a correlation between the PAINAD scale (numeric, binary, and recoded) and sTNF-RII and sIgA (p < 0.001). No association between the sociodemographic and clinical variables and the PAINAD scale was found (p > 0.05). Between 97.3% and 96.2% of patients with pain on the PAINAD scale also showed pain based on the sTNF-RII levels; in all of them, sIgA levels did not fit the logistic models. Therefore, the correlation highlights the usefulness of this scale and confirms the usefulness of sTNF-RII and sIgA as biomarkers of pain.

Moderate Beer Consumption Modifies Tumoral Growth Parameters and Pyrrolidone Carboxypeptidase Type-I and Type-II Specific Activities in the Hypothalamus-Pituitary-Mammary Gland Axis in an Animal Model of Breast Cancer.

AIMS: To determine the effect of moderate alcoholic and nonalcoholic beer consumption on tumoral growth parameters, the histopathology, pyrrolidone carboxypeptidase type I (Pcp I), and type II (Pcp II) specific activities in the hypothalamus-pituitary-mammary gland axis, and the circulating levels of estradiol (E2) and progesterone (P4) in rats with N-methyl-N-nitrosourea (NMU) induced mammary tumors. MATERIAL AND METHODS: Food and drink intake, weight gain and tumor growth parameters were collected. The malignant phenotype of the tumor was performed using the Scarff-Bloom-Richardson grading method. Pcp specific activities were fluorometrically analyzed using pyroglutamyl-ß-naphthylamide as substrate. Circulating steroid hormones were determined. RESULTS: Differences were found in tumoral parameters, depending on the drink. Animals that were given alcohol-containing beer (A/C) beer to drink showed the lowest values of hypothalamic Pcp I, in association with the lowest levels of circulating E2. The significant decrease in Pcp I activity in all NMU-treated groups suggest a clear role of the Pcp I in the tumoral process, and A/C beer interferes with it. DISCUSSION: Moderate consumption of alcoholic beer would have beneficial effects against mammary tumors through the modification of the endocrine status mediated by GnRH due to changes on Pcp I and II activities at different levels.

Depression as a Risk Factor for Dementia and Alzheimer's Disease.

Preventing the onset of dementia and Alzheimer's disease (AD), improving the diagnosis, and slowing the progression of these diseases remain a challenge. The aim of this study was to elucidate the association between depression and dementia/AD and to identify possible relationships between these diseases and different sociodemographic and clinical features. In this regard, a case-control study was conducted in Spain in 2018-2019. The definition of a case was: A person ≥ 65 years old with dementia and/or AD and a score of 5-7 on the Global Deterioration Scale (GDS). The sample consisted of 125 controls; among the cases, 96 had dementia and 74 had AD. The predictor variables were depression, dyslipidemia, type 2 diabetes mellitus, and hypertension. The results showed that depression, diabetes mellitus, and older age were associated with an increased likelihood of developing AD, with an Odds Ratio (OR) of 12.9 (95% confidence interval (CI): 4.3-39.9), 2.8 (95% CI: 1.1-7.1) and 1.15 (95% CI: 1.1-1.2), respectively. Those subjects with treated dyslipidemia were less likely to develop AD (OR 0.47, 95% CI: 0.22-1.1). Therefore, depression and diabetes mellitus increase the risk of dementia, whereas treated dyslipidemia has been shown to reduce this risk.

Correlation between biomarkers of pain in saliva and PAINAD scale in elderly people with cognitive impairment and inability to communicate: descriptive study protocol.

INTRODUCTION: Pain is an under-diagnosed problem in elderly people, especially in those with cognitive impairment who are unable to verbalise their pain. Although the Pain assessment in advanced dementia scale (PAINAD) scale is a tool recognised for its clinical interest in this type of patients, its correlation with the saliva biomarkers reinforced its utility. The aim of this research will be to correlate the scores of this scale with the levels of biomarkers of pain found in saliva samples of patients with cognitive impairment and inability to communicate. METHODS AND ANALYSIS: This is an observational study. The level of pain will be evaluated using the PAINAD scale. Moreover, pain biomarkers, in particular secretory IgA and soluble tumour necrosis factor receptor type II, will be determined in saliva. Both assessments will be conducted in 75 patients aged over 65 years with advanced cognitive impairment and inability to communicate. The PAINAD scores will be correlated with the levels of these biomarkers of pain. A control group consisting of 75 healthy subjects aged over 65 years will be included in the study. Moreover, sociodemographic variables and variables related to pain, dementia and other clinical conditions will be recorded. The analysis will be performed with the statistical package SPSS V.22 and the software R. ETHICS AND DISSEMINATION: The study has been reviewed and approved by the Andalusian Human Research Ethics Committee. In addition, this study has been financed by the Junta de Andalucía through a regional health research fund (Research code: PI-0357-2017). The results will be actively disseminated trough a high-impact journal in our study area, conference presentations and social media.

Neoadjuvant chemotherapy modifies serum angiotensinase activities in women with breast cancer.

PURPOSE: The aim of this study was to investigate the putative changes in serum angiotensinase activities (aminopeptidase N, APN; aminopeptidase B, APB; aminopeptidase A, APA; aspartyl aminopeptidase, ASAP) involved in the renin-angiotensin system (RAS) in women with breast cancer treated or not with a neoadjuvant therapy of paclitaxel and anthracycline and in healthy women volunteers. METHODS: We fluorometrically analysed serum APN, APB, APA and ASAP activities using their corresponding aminoacyl-ß-naphthylamides as substrates in women with breast cancer treated with a neoadjuvant therapy of paclitaxel and anthracycline. RESULTS: When compared with healthy controls, women with breast cancer not treated with neoadjuvant chemotherapy, showed a decrease in angiotensinase activity, which support the putative increase of angiotensin II (Ang II) levels, indicating that the tumour process would favour the development of the disease. Also, an increase in APN and APB activities was observed, which support a role for angiotensin IV (Ang IV). In women treated with a neoadjuvant therapy, we described an increase in ASAP and APA activities, supporting the idea that this treatment increases Ang II catabolism. The resulting decrease in Ang II level could lead to an inhibition of the tumour growth. CONCLUSION: Present results show changes in serum angiotensinase activities in women with breast cancer and in women with breast cancer treated with a neoadjuvant therapy of paclitaxel and anthracycline. Therefore, considerable attention should be focused on the development of RAS blockade therapy as a new strategy for breast cancer treatment.

Putative relationship between hormonal status and serum pyrrolidone carboxypeptidase activity in pre- and post- menopausal women with breast cancer.

In breast cancer, hormonal changes are rather constant in post-menopausal women since they tend to vary only over long time spans. However, in pre-menopausal women, the development of breast cancer is associated with hormonal physiological variations. The aim of the present work was to analyse the changes in circulating levels of gonadotropin-releasing hormone (GnRH), follicle-stimulating hormone (FSH) and luteinizing hormone (LH) in pre- and post-menopausal women that were healthy or with breast cancer, and their connection to serum pyrrolidone carboxypeptidase (Pcp) activity. We observed significant changes in the hormonal profile in post-menopausal women with breast cancer compared to the control group. In pre-menopausal women, we found significant changes in circulating GnRH levels with respect to the healthy group. Our present results support the existence of neuroendocrine misregulation that could be involved in tumour progression, with Pcp being a potentially new pharmacological target in breast cancer treatments.