Stakeholder Insights in Alzheimer's Disease: Natural Language Processing of Social Media Conversations

Clinical Characterization of Veterans With Alzheimer Disease by Disease Severity in the United States

PURPOSE

We aimed to examine the clinical characteristics of US veterans who underwent neurocognitive test score-based assessments of Alzheimer disease (AD) stage in the Veterans Affairs Healthcare System (VAHS).

METHODS

Test dates for specific stages of AD were referenced as index dates to study behavioral and psychological symptoms of dementia (BPSD) and other patient characteristics related to utilization/work-up and time to death.

PATIENTS

We identified veterans with AD and neurocognitive evaluations using the VAHS Electronic Health Record (EHR).

RESULTS

Anxiety and sleep disorders/disturbances were the most documented BPSDs across all AD severity stages. Magnetic resonance imaging, neurology and psychiatry consultations, and neuropsychiatric evaluations were slightly higher in veterans with mild AD than in those at later stages. The overall average time to death from the first AD severity record was 5 years for mild and 4 years for moderate/severe AD.

CONCLUSION

We found differences in clinical symptoms, healthcare utilization, and survival among the mild, moderate, and severe stages of AD. These differences are limited by the low documentation of BPSDs among veterans with test score-based AD stages. These data support the hypothesis that our cohorts represent coherent subgroups of patients with AD based on disease severity.

Assessing Quality of Life, Economic Burden, and Independence Across the Alzheimer's Disease Continuum Using Patient-Caregiver Dyad Surveys

Background

Alzheimer's disease (AD) and mild cognitive impairment (MCI) have negative quality of life (QoL) and economic impacts on patients and their caregivers and may increase along the disease continuum from MCI to mild, moderate, and severe AD.

Objective

To assess how patient and caregiver QoL, indirect and intangible costs are associated with MCI and AD severity.

Methods

An on-line survey of physician-identified patient-caregiver dyads living in the United States was conducted from June-October 2022 and included questions to both patients and their caregivers. Dementia Quality of Life Proxy, the Care-related Quality of Life, Work Productivity and Activity Impairment, and Dependence scale were incorporated into the survey. Regression analyses investigated the association between disease severity and QoL and cost outcomes with adjustment for baseline characteristics.

Results

One-hundred patient-caregiver dyads were assessed with the survey (MCI, n = 27; mild AD, n = 27; moderate AD, n = 25; severe AD, n = 21). Decreased QoL was found with worsening severity in patients (p < 0.01) and in unpaid (informal) caregivers (n = 79; p = 0.02). Dependence increased with disease severity (p < 0.01). Advanced disease severity was associated with higher costs to employers (p = 0.04), but not with indirect costs to caregivers. Patient and unpaid caregiver intangible costs increased with disease severity (p < 0.01). A significant trend of higher summed costs (indirect costs to caregivers, costs to employers, intangible costs to patients and caregivers) in more severe AD was observed (p < 0.01).

Conclusions

Patient QoL and functional independence and unpaid caregiver QoL decrease as AD severity increases. Intangible costs to patients and summed costs increase with disease severity and are highest in severe AD.

What can we learn from a Chinese social media used by glaucoma patients?

PURPOSE

Our study aims to discuss glaucoma patients' needs and Internet habits using big data analysis and Natural Language Processing (NLP) based on deep learning (DL).

METHODS

In this retrospective study, we used web crawler technology to crawl glaucoma-related topic posts from the glaucoma bar of Baidu Tieba, China. According to the contents of topic posts, we classified them into posts with seeking medical advice and without seeking medical advice (social support, expressing emotions, sharing knowledge, and others). Word Cloud and frequency statistics were used to analyze the contents and visualize the keywords of topic posts. Two DL models, Bidirectional Long Short-Term Memory (Bi-LSTM) and Bidirectional Encoder Representations from Transformers (BERT), were trained to identify the posts seeking medical advice. The evaluation matrices included: accuracy, F1 value, and the area under the ROC curve (AUC).

RESULTS

A total of 10,892 topic posts were included, among them, most were seeking medical advice (N = 7071, 64.91%), and seeking advice regarding symptoms or examination (N = 4913, 45.11%) dominated the majority. The following were searching for social support (N = 2362, 21.69%), expressing emotions (N = 497, 4.56%), and sharing knowledge (N = 527, 4.84%) in sequence. The word cloud analysis results showed that ocular pressure, visual field, examination, and operation were the most frequent words. The accuracy, F1 score, and AUC were 0.891, 0.891, and 0.931 for the BERT model, 0.82, 0.821, and 0.890 for the Bi-LSTM model.

CONCLUSION

Social media can help enhance the patient-doctor relationship by providing patients' concerns and cognition about glaucoma in China. NLP can be a powerful tool to reflect patients' focus on diseases. DL models performed well in classifying Chinese medical-related texts, which could play an important role in public health monitoring.

Understanding Barriers Along the Patient Journey in Alzheimer's Disease Using Social Media Data

INTRODUCTION

We speculated that social media data from Alzheimer's disease (AD) stakeholders (patients, caregivers, and clinicians) could identify barriers along the patient journey in AD, and that insights gained may help devise strategies to remove barriers, and ultimately improve the patient journey.

METHODS

Our sample was drawn from a repository of social media posts extracted from 112 public sources between January 1998 and December 2021 using natural language processing text-mining algorithms. The patient journey was classified into three phases: (1) early signs/experiences (Early Signs); (2) screening/assessment/diagnosis (Screening); and (3) treatment/management (Treatment). In the Early Signs phase, issues/challenges derived from a conceptual AD identification framework (ADIF) were examined. In subsequent phases, behavioral/psychiatric challenges, access/barriers to health care, screening/diagnostic methods, and symptomatic treatments for AD were identified. Posts were classified by AD stakeholder type or disease stage, if possible.

RESULTS

We identified 225,977 AD patient journey-related social media posts. Anxiety was a predominant issue/challenge in all patient journey phases. In the Screening and Treatment phases combined, access/barriers to care were described in 16% of posts; unwillingness/resistance to seeking care was a major barrier (≥ 75% of access-related posts across all stakeholders). Commonly identified structural barriers (e.g., affordability/cost, geography/transportation/distance) were more common in patient/caregiver posts than clinician posts. Among Screening-related posts, imaging/scans were commonly mentioned by all stakeholders; biomarkers were more commonly mentioned by patients than clinicians. Treatment-related concerns were identified in 17% of stakeholder-specified posts that named pharmacological agents/classes for the symptomatic management of AD.

CONCLUSION

This descriptive analysis of out-of-clinic experiences reflected in AD social media posts found that unwillingness/resistance to seeking care was a key barrier, followed by structural barriers to health care, such as affordability/cost. Insights from the lived experiences of AD stakeholders are valuable and highlight the need to improve the patient journey in AD and ease patient and caregiver burden.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.