Differential diagnosis between dementia and psychiatric disorders: Diagnostic criteria and supplementary exams. Recommendations of the Scientific Department of Cognitive Neurology and Aging of the Brazilian Academy of Neurology

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Validation study of the Persian version of behavioral pathology in Alzheimer's Disease Rating scale (BEHAVE-AD) and the empirical BHAVE-AD (E-BEHAVE-AD)

INTRODUCTION

Behavioral and psychological symptoms of dementia (BPSD) are observed in more than 90% of patients with Alzheimer's disease (AD). BPSDs are remediable if detected early and managed appropriately. Behavioral Pathology in Alzheimer's disease Rating Scale (BEHAVE-AD) and Empirical BEHAVE-AD (E-BEHAVE-AD) were designed to identify BPSD. The aim of this study is to validate and prepare BEHAVE-AD and E-BEHAVE-AD in Persian language for clinical and research applications.

METHOD

120 patients were selected through a combination of intentional and convenience sampling. All participants should fulfill the NINCDS-ADRDA Work Group criteria for a clinical diagnosis of Alzheimer's disease. Functional Assessment Staging Tool (FAST) was used to determine the rate of AD progression. All patients were evaluated using the BEHAVE-AD and E-BEHAVE-AD questionnaires, as well as the Persian version of the Neuropsychiatric Inventory Questionnaire (NPI-Q) and Mini-Mental State Examination (MMSE). The Content Validity Index (CVI) is determined based on the compatibility of the Persian and the original version of the two scales according to the opinion of expert panels. Correlation of MMSE with BEHAVE-AD and E-BEHAVE-AD as well as the BPSD pattern on AD progression continuum by FAST were considered as indices of construct validity. Concurrent validity was estimated by correlating NPI-Q scores with BEHAVE-AD and E-BEHAVE-AD scores. For both scales, interrater reliability was extracted as a reliability index.

RESULTS

Pearson correlation coefficients for the BEHAVE-AD scale were as follows: with NPI-Q (r = 0.77, p-value <0.01), with MMSE (r = -0.34, p-value <0.01), indicating concurrent and construct validity, respectively. The result for E-BEHAVE-AD was as follows: with NPI-Q-total (r = 0.59, p-value <0.01), and with MMSE (r = 0.31, p-value <0. 01). BEHAVE-AD and E-BEHAVE-AD scores increased in parallel with AD severity according to FAST, but not on the most severe AD stage. The area under the curve was estimated to be 0.84 (p-value <0.001) for BEHAVE-AD and 0.78 (p-value <0.001) for E-BEHAVE-AD. Correlation between BEHAVE-AD and E-BEHAVE-AD scores ranged from 0.45 to 0.63. The inter-rater reliability index ranged from 0.88 to 0.99 for BEHAVE-AD and from 0.74 to 0.95 for E-BEHAVE-AD.

CONCLUSIONS

The Persian version of BEHAVE-AD and E-BEHAVE-AD is valid and reliable for the assessment of BPSD in patients with AD.

Alzheimer's Disease-Related Metabolic Pattern in Diverse Forms of Neurodegenerative Diseases

Dementia is broadly characterized by cognitive and psychological dysfunction that significantly impairs daily functioning. Dementia has many causes including Alzheimer’s disease (AD), dementia with Lewy bodies (DLB), and frontotemporal lobar degeneration (FTLD). Detection and differential diagnosis in the early stages of dementia remains challenging. Fueled by AD Neuroimaging Initiatives (ADNI) (Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. As such, the investigators within ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report.), a number of neuroimaging biomarkers for AD have been proposed, yet it remains to be seen whether these markers are also sensitive to other types of dementia. We assessed AD-related metabolic patterns in 27 patients with diverse forms of dementia (five had probable/possible AD while others had atypical cases) and 20 non-demented individuals. All participants had positron emission tomography (PET) scans on file. We used a pre-trained machine learning-based AD designation (MAD) framework to investigate the AD-related metabolic pattern among the participants under study. The MAD algorithm showed a sensitivity of 0.67 and specificity of 0.90 for distinguishing dementia patients from non-dementia participants. A total of 18/27 dementia patients and 2/20 non-dementia patients were identified as having AD-like patterns of metabolism. These results highlight that many underlying causes of dementia have similar hypometabolic pattern as AD and this similarity is an interesting avenue for future research.

Memory complaints at primary care in a middle-income country: clinical and neuropsychological characterization

There are different causes of memory complaints in the elderly, such as subjective cognitive decline (SCD), mild cognitive impairment (MCI) or dementia.

OBJECTIVE

1) To characterize individuals with memory complaints in a mid-sized city in Brazil, through clinical, cognitive and functional assessment; 2) to compare SCD individuals with MCI and dementia patients in terms of clinical and cognitive variables.

METHODS

We consecutively included individuals aged ≥50 years, with memory complaints (spontaneous or inquired). Subjects who scored ≥25 on the Memory Complaint Questionnaire or who had spontaneous memory complaints were selected. Participants underwent a semi-structured interview, the Mini-Mental State Examination, Figure Memory Test for visual episodic memory, Clock Drawing Test, Category Fluency (Animals), Neuropsychiatric Inventory, and functional assessment. Individuals were classified as SCD, MCI or dementia. We did not include individuals with previous diagnosis of dementia.

RESULTS

The final sample consisted of 91 subjects (73.6% women; mean age 67.6±9.8 years): 14.3% had spontaneous complaints and 85.7% had inquired complaints. The most common comorbidities were hypertension (69.2%), diabetes (36.3%), and dyslipidemia (24.2%). Low levels of vitamin B12 and hypothyroidism were found in 26.4 and 16.5%, respectively. Regarding cognitive diagnosis, 16.5% of the sample were classified as SCD, 49.4% as MCI and 34.1% as dementia. MCI and dementia were identified in five (38.5%) and seven (53.4%) patients with spontaneous complaint, respectively.

CONCLUSIONS

MCI and dementia are frequently underdiagnosed. Potential reversible causes of cognitive decline are common. The diagnosis of dementia is highly frequent among individuals with spontaneous memory complaints.

Depressive symptoms and cognitive deficits in a cancer patient submitted to chemotherapy with 5-Fluoracil: a case report

Cognitive deficits in cancer patients can be related to depression, anxiety, and the side effects of treatments such as fatigue. In this case report, we described an elderly patient with rectal adenocarcinoma, which presented depressive symptoms and memory complaints after treatment with 5-Fluoracil and Leucovorin. Depressive symptoms improved after two months but cognitive and functional impairment worsened suggesting the diagnosis of mild dementia. Structural and functional brain changes were seen on neuroimaging exams. Rivastigmine was introduced up to 12 mg/day, and after a one-year follow up the patient remained stable. Cognitive deficits can be a consequence of cancer therapies and a protocol to investigate deficits cognitive could be useful to the diferential diagnosis and management of elderly cancer patients submitted to chemotherapy.