Identification of dementia and MCI cases in health information systems: An Italian validation study

Real-World Insights Into Dementia Diagnosis Trajectory and Clinical Practice Patterns Unveiled by Natural Language Processing: Development and Usability Study

Background

Understanding the dementia disease trajectory and clinical practice patterns in outpatient settings is vital for effective management. Knowledge about the path from initial memory loss complaints to dementia diagnosis remains limited.

Objective

This study aims to (1) determine the time intervals between initial memory loss complaints and dementia diagnosis in outpatient care, (2) assess the proportion of patients receiving cognition-enhancing medication prior to dementia diagnosis, and (3) identify patient and provider characteristics that influence the time between memory complaints and diagnosis and the prescription of cognition-enhancing medication.

Methods

This retrospective cohort study used a large outpatient electronic health record (EHR) database from the University of Connecticut Health Center, covering 2010-2018, with a cohort of 581 outpatients. We used a customized deep learning-based natural language processing (NLP) pipeline to extract clinical information from EHR data, focusing on cognition-related symptoms, primary caregiver relation, and medication usage. We applied descriptive statistics, linear, and logistic regression for analysis.

Results

The NLP pipeline showed precision, recall, and F1-scores of 0.97, 0.93, and 0.95, respectively. The median time from the first memory loss complaint to dementia diagnosis was 342 (IQR 200-675) days. Factors such as the location of initial complaints and diagnosis and primary caregiver relationships significantly affected this interval. Around 25.1% (146/581) of patients were prescribed cognition-enhancing medication before diagnosis, with the number of complaints influencing medication usage.

Conclusions

Our NLP-guided analysis provided insights into the clinical pathways from memory complaints to dementia diagnosis and medication practices, which can enhance patient care and decision-making in outpatient settings.

Incidence and Prevalence of Dementia: A 2015-2020 Population-Based Study in the Campania Region of Italy

OBJECTIVE

The aims of this study were to provide population-based estimates of prevalence and incidence of any dementia and Alzheimer's dementia (AD) in the Campania region (South Italy) and to validate towards a clinical registry.

METHODS

This was a population-based study, using routinely collected healthcare data of individuals living in the Campania region (South Italy) from 2015 to 2020. We included individuals aged ≥65 years alive at the prevalence day (January 1, 2021) who had at least one administrative record for dementia and/or AD from 2015 to 2020. Age-and sex-standardised prevalence rates were calculated using direct standardisation method (European population in 2020 as the reference population). To estimate the incidence, we tested three possible algorithms, which differed for the duration of the time interval between study baseline (January 1, 2015) and index date (first record for dementia and/or AD in administrative databases). We employed a clinical database for the validation of our algorithms towards neuropsychological test results.

RESULTS

Among individuals aged over 65 years, 80,392 had dementia, of which 35,748 had AD. The age- and sex-standardised prevalence rates per 1,000 individuals for any dementia and AD were 77.64 (95% confidence interval [CI] = 77.57; 77.68) and 34.05 (95% CI = 34.01; 34.09), respectively. There were 82.10 incident cases of any dementia per 100,000 per year (0.79 sensitivity and 0.62 specificity) and 59.89 incident cases of AD per 100,000 per year (0.80 sensitivity and 0.59 specificity). The capture-recapture method showed a very low number of undetected cases (1.7% for any dementia and 3.0% for AD). Our algorithms showed acceptable performance with the area under the curve ranging from 0.59 to 0.72 and a double likelihood ratio of correctly identifying individuals above and below mini-mental status examination (MMSE) standard cut-offs (24 and 26).

CONCLUSIONS

Prevalence and incidence of any dementia and AD in the Campania region (South Italy) from 2015 to 2020 are in line with previous estimates from other countries. Our algorithm, integrating administrative and clinical data, holds potential for assessing dementia's epidemiological burden, identifying risk factors, planning healthcare access, and developing prevention strategies.

A new national survey of centers for cognitive disorders and dementias in Italy

INTRODUCTION

A new national survey has been carried out by the Italian Centers for Cognitive Disorders and Dementias (CCDDs). The aim of this new national survey is to provide a comprehensive description of the characteristics, organizational aspects of the CCDDs, and experiences during the COVID-19 pandemic.

METHODS

A list of all national CCDDs was requested from the delegates of each Italian region. The online questionnaire is divided in two main sections: a profile section, containing information on location and accessibility, and a data collection form covering organization, services, treatments, activities, and any service interruptions caused by the COVID-19 outbreak.

RESULTS

In total, 511 out of 534 (96%) facilities completed the profile section, while 450 out of 534 (84%) CCDDs also completed the data collection form. Almost half of the CCDDs (55.1%) operated for 3 or fewer days a week. About one-third of the facilities had at least two professional figures among neurologists, geriatricians and psychiatrists. In 2020, only a third of facilities were open all the time, but in 2021, two-thirds of the facilities were open.

CONCLUSION

This paper provides an update on the current status of CCDDs in Italy, which still shows considerable heterogeneity. The survey revealed a modest improvement in the functioning of CCDDs, although substantial efforts are still required to ensure the diagnosis and care of patients with dementia.

Incidence and Risk Factors Epilepsy in Patients with Dementia: A Population-Based Study Using Regional Healthcare Databases in Umbria

Background

Dementia is prevalent among the elderly, also representing a risk for seizures/epilepsy. Estimations of epilepsy risk in dementia patients are not widely available.

Objective

Our research aims to ascertain the incidence of epilepsy and its associated risk factors in subjects with dementia in the Umbria region, based on data from healthcare databases.

Methods

In this retrospective study based on the healthcare administrative database of Umbria, we identified all patients diagnosed with dementia from 2013 to 2017, based on ICD-9-CM codes. For epilepsy ascertainment, we used a validated algorithm that required an EEG and the prescription of one or more anti-seizure medications post-dementia diagnosis. A case-control analysis was conducted, matching five non-dementia subjects by gender and age to each dementia patient. Cox proportional hazards models were then utilized in the analysis.

Results

We identified 7,314 dementia cases, also including 35,280 age- and sex-matched control subjects. Out of patients with dementia, 148 individuals (2.02%) were diagnosed with epilepsy. We observed a progressive increase in the cumulative incidence of seizures over time, registering 1.45% in the first year following the diagnosis, and rising to 1.96% after three years. Analysis using Cox regression revealed a significant association between the development of epilepsy and dementia (HR = 4.58, 95% CI = 3.67-5.72). Additional risk factors were male gender (HR = 1.35, 95% CI = 1.07-1.69) and a younger age at dementia onset (HR = 1.03, 95% CI=1.02-1.04).

Conclusions

Dementia increases epilepsy risk, especially with early onset and male gender. Clinicians should have a low threshold to suspect seizures in dementia cases.