Challenges for Optimizing Real-World Evidence in Alzheimer's Disease: The ROADMAP Project

Semantic Harmonization of Alzheimer's Disease Datasets Using AD-Mapper

Background

Despite numerous past endeavors for the semantic harmonization of Alzheimer's disease (AD) cohort studies, an automatic tool has yet to be developed.

Objective

As cohort studies form the basis of data-driven analysis, harmonizing them is crucial for cross-cohort analysis. We aimed to accelerate this task by constructing an automatic harmonization tool.

Methods

We created a common data model (CDM) through cross-mapping data from 20 cohorts, three CDMs, and ontology terms, which was then used to fine-tune a BioBERT model. Finally, we evaluated the model using three previously unseen cohorts and compared its performance to a string-matching baseline model.

Results

Here, we present our AD-Mapper interface for automatic harmonization of AD cohort studies, which outperformed a string-matching baseline on previously unseen cohort studies. We showcase our CDM comprising 1218 unique variables.

Conclusion

AD-Mapper leverages semantic similarities in naming conventions across cohorts to improve mapping performance.

Health economic modeling for Alzheimer's disease: Expert perspectives

The successful development of an economic model for the evaluation of future Alzheimer's disease (AD) interventions is critical to accurately inform policy makers and payers. As our understanding of AD expands, this becomes an increasingly complex and challenging goal. Advances in diagnostic techniques for AD and the prospect of disease-modifying treatments raise an urgent need to define specifications for future economic models and to ensure that the necessary data to populate them are available. This Perspective article provides expert opinions from health economists and governmental agency representatives on how future economic models for AD might be structured, validated, and reported. We aim to stimulate much-needed discussion about the detailed specification of future health economic models for AD.

Predictors of response to acetylcholinesterase inhibitors in dementia: A systematic review

Background

The mainstay of therapy for many neurodegenerative dementias still relies on acetylcholinesterase inhibitors (AChEI); however, there is debate on various aspects of such treatment. A huge body of literature exists on possible predictors of response, but a comprehensive review is lacking. Therefore, our aim is to perform a systematic review of the predictors of response to AChEI in neurodegenerative dementias, providing a categorization and interpretation of the results.

Methods

We conducted a systematic review of the literature up to December 31st, 2021, searching five different databases and registers, including studies on rivastigmine, donepezil, and galantamine, with clearly defined criteria for the diagnosis of dementia and the response to AChEI therapy. Records were identified through the string: predict * AND respon * AND (acetylcholinesterase inhibitors OR donepezil OR rivastigmine OR galantamine). The results were presented narratively.

Results

We identified 1,994 records in five different databases; after exclusion of duplicates, title and abstract screening, and full-text retrieval, 122 studies were finally included.

Discussion

The studies show high heterogeneity in duration, response definition, drug dosage, and diagnostic criteria. Response to AChEI seems associated with correlates of cholinergic deficit (hallucinations, fluctuating cognition, substantia innominate atrophy) and preserved cholinergic neurons (faster alpha on REM sleep EEG, increased anterior frontal and parietal lobe perfusion after donepezil); white matter hyperintensities in the cholinergic pathways have shown inconsistent results. The K-variant of butyrylcholinesterase may correlate with better response in late stages of disease, while the role of polymorphisms in other genes involved in the cholinergic system is controversial. Factors related to drug availability may influence response; in particular, low serum albumin (for donepezil), CYP2D6 variants associated with reduced enzymatic activity and higher drug doses are the most consistent predictors, while AChEI concentration influence on clinical outcomes is debatable. Other predictors of response include faster disease progression, lower serum cholesterol, preserved medial temporal lobes, apathy, absence of concomitant diseases, and absence of antipsychotics. Short-term response may predict subsequent cognitive response, while higher education might correlate with short-term good response (months), and long-term poor response (years). Age, gender, baseline cognitive and functional levels, and APOE relationship with treatment outcome is controversial.

Cohort profile: the Norwegian Registry of Persons Assessed for Cognitive Symptoms (NorCog) - a national research and quality registry with a biomaterial collection

PURPOSE

The Norwegian Registry of Persons Assessed for Cognitive Symptoms (NorCog) was established to harmonise and improve the quality of diagnostic practice across clinics assessing persons with cognitive symptoms in Norwegian specialist healthcare units and to establish a large research cohort with extensive clinical data.

PARTICIPANTS

The registry recruits patients who are referred for assessment of cognitive symptoms and suspected dementia at outpatient clinics in Norwegian specialist healthcare units. In total, 18 120 patients have been included in NorCog during the period of 2009-2021. The average age at inclusion was 73.7 years. About half of the patients (46%) were diagnosed with dementia at the baseline assessment, 35% with mild cognitive impairment and 13% with no or subjective cognitive impairment; 7% received other specified diagnoses such as mood disorders.

FINDINGS TO DATE

All patients have a detailed baseline characterisation involving lifestyle and demographic variables; activities of daily living; caregiver situation; medical history; medication; psychiatric, physical and neurological examinations; neurocognitive testing; blood laboratory work-up; and structural or functional brain imaging. Diagnoses are set according to standardised diagnostic criteria. The research biobank stores DNA and blood samples from 4000 patients as well as cerebrospinal fluid from 800 patients. Data from NorCog have been used in a wide range of research projects evaluating and validating dementia-related assessment tools, and identifying patient characteristics, symptoms, functioning and needs, as well as caregiver burden and requirement of available resources.

FUTURE PLANS

The finish date of NorCog was originally in 2029. In 2021, the registry's legal basis was reformalised and NorCog got approval to collect and keep data for as long as is necessary to achieve the purpose of the registry. In 2022, the registry underwent major changes. Paper-based data collection was replaced with digital registration, and the number of variables collected was reduced. Future plans involve expanding the registry to include patients from primary care centres.

Estimation of the epidemiology of dementia and associated neuropsychiatric symptoms by applying machine learning to real-world data

INTRODUCTION

Incidence rates of dementia-related neuropsychiatric symptoms (NPS) are not known and this hampers the assessment of their population burden. The objective of this study was to obtain an approximate estimate of the population incidence and prevalence of both dementia and NPS.

METHODS

Given the dynamic nature of the population with dementia, a retrospective study was conducted within the database of the Basque Health Service (real-world data) at the beginning and end of 2019. Validated random forest models were used to identify separately depressive and psychotic clusters according to their presence in the electronic health records of all patients diagnosed with dementia.

RESULTS

Among the 631,949 individuals over 60 years registered, 28,563 were diagnosed with dementia, of whom 15,828 (55.4%) showed psychotic symptoms and 19,461 (68.1%) depressive symptoms. The incidence of dementia in 2019 was 6.8/1000 person-years. Most incident cases of depressive (72.3%) and psychotic (51.9%) NPS occurred in cases of incident dementia. The risk of depressive-type NPS grows with years since dementia diagnosis, living in a nursing home, and female sex, but falls with older age. In the psychotic cluster model, the effects of male sex, and older age are inverted, both increasing the probability of this type of symptoms.

CONCLUSIONS

The stigmatization factor conditions the social and attitudinal environment, delaying the diagnosis of dementia, preventing patients from receiving adequate care and exacerbating families' suffering. This study evidences the synergy between big data and real-world data for psychiatric epidemiological research.

ADataViewer: exploring semantically harmonized Alzheimer's disease cohort datasets

BACKGROUND

Currently, Alzheimer's disease (AD) cohort datasets are difficult to find and lack across-cohort interoperability, and the actual content of publicly available datasets often only becomes clear to third-party researchers once data access has been granted. These aspects severely hinder the advancement of AD research through emerging data-driven approaches such as machine learning and artificial intelligence and bias current data-driven findings towards the few commonly used, well-explored AD cohorts. To achieve robust and generalizable results, validation across multiple datasets is crucial.

METHODS

We accessed and systematically investigated the content of 20 major AD cohort datasets at the data level. Both, a medical professional and a data specialist, manually curated and semantically harmonized the acquired datasets. Finally, we developed a platform that displays vital information about the available datasets.

RESULTS

Here, we present ADataViewer, an interactive platform that facilitates the exploration of 20 cohort datasets with respect to longitudinal follow-up, demographics, ethnoracial diversity, measured modalities, and statistical properties of individual variables. It allows researchers to quickly identify AD cohorts that meet user-specified requirements for discovery and validation studies regarding available variables, sample sizes, and longitudinal follow-up. Additionally, we publish the underlying variable mapping catalog that harmonizes 1196 unique variables across the 20 cohorts and paves the way for interoperable AD datasets.

CONCLUSIONS

In conclusion, ADataViewer facilitates fast, robust data-driven research by transparently displaying cohort dataset content and supporting researchers in selecting datasets that are suited for their envisioned study. The platform is available at https://adata.scai.fraunhofer.de/ .

Developing a Dementia Platform Databank Using Multiple Existing Cohorts

This study was conducted as a pilot project to evaluate the feasibility of building an integrate dementia platform converging preexisting dementia cohorts from several variable levels. The following four cohorts were used to develop this pilot platform: 1) Clinical Research Center for Dementia of South Korea (CREDOS), 2) Korean Brain Aging Study for Early Diagnosis and Prediction of Alzheimer's disease (K-BASE), 3) Environmental Pollution-induced Neurological Effects (EPINEF) study, and 4) a prospective registry in Dementia Platform Korea project (DPKR). A total of 29916 patients were included in the platform with 348 integrated variables. Among participants, 13.9%, 31.5%, and 44.2% of patients had normal cognition, mild cognitive impairment, and dementia, respectively. The mean age was 72.4 years. Females accounted for 65.7% of all patients. Those with college or higher education and those without problems in reading or writing accounted for 12.3% and 46.8%, respectively. Marital status, cohabitation, family history of Parkinson's disease, smoking and drinking status, physical activity, sleep status, and nutrition status had rates of missing information of 50% or more. Although individual cohorts were of the same domain and of high quality, we found there were several barriers to integrating individual cohorts, including variability in study variables and measurements. Although many researchers are trying to combine pre-existing cohorts, the process of integrating past data has not been easy. Therefore, it is necessary to establish a protocol with considerations for data integration at the cohort establishment stage.

Systems thinking in health technology assessment: a scoping review

OBJECTIVE

Our objective was to assess how, and to what extent, a systems-level perspective is considered in decision-making processes for health interventions by illustrating how studies define the boundaries of the system in their analyses and by defining the decision-making context in which a systems-level perspective is undertaken.

METHOD

We conducted a scoping review following the Joanna Briggs Institute methodology. MEDLINE, EMBASE, Cochrane Library, and EconLit were searched and key search concepts included decision making, system, and integration. Studies were classified according to an interpretation of the "system" of analysis used in each study based on a four-level model of the health system (patient, care team, organization, and/or policy environment) and using categories (based on intervention type and system impacts considered) to describe the decision-making context.

RESULTS

A total of 2,664 articles were identified and 29 were included for analysis. Most studies (16/29; 55%) considered multiple levels of the health system (i.e., patient, care team, organization, environment) in their analysis and assessed multiple classes of interventions versus a single class of intervention (e.g., pharmaceuticals, screening programs). Approximately half (15/29; 52%) of the studies assessed the influence of policy options on the system as a whole, and the other half assessed the impact of interventions on other phases of the disease pathway or life trajectory (14/29; 48%).

CONCLUSIONS

We found that systems thinking is not common in areas where health technology assessments (HTAs) are typically conducted. Against this background, our study demonstrates the need for future conceptualizations and interpretations of systems thinking in HTA.

Ethical and Social Implications of Using Predictive Modeling for Alzheimer's Disease Prevention: A Systematic Literature Review

BACKGROUND

The therapeutic paradigm in Alzheimer's disease (AD) is shifting from symptoms management toward prevention goals. Secondary prevention requires the identification of individuals without clinical symptoms, yet "at-risk" of developing AD dementia in the future, and thus, the use of predictive modeling.

OBJECTIVE

The objective of this study was to review the ethical concerns and social implications generated by this new approach.

METHODS

We conducted a systematic literature review in Medline, Embase, PsycInfo, and Scopus, and complemented it with a gray literature search between March and July 2018. Then we analyzed data qualitatively using a thematic analysis technique.

RESULTS

We identified thirty-one ethical issues and social concerns corresponding to eight ethical principles: (i) respect for autonomy, (ii) beneficence, (iii) non-maleficence, (iv) equality, justice, and diversity, (v) identity and stigma, (vi) privacy, (vii) accountability, transparency, and professionalism, and (viii) uncertainty avoidance. Much of the literature sees the discovery of disease-modifying treatment as a necessary and sufficient condition to justify AD risk assessment, overlooking future challenges in providing equitable access to it, establishing long-term treatment outcomes and social consequences of this approach, e.g., medicalization. The ethical/social issues associated specifically with predictive models, such as the adequate predictive power and reliability, infrastructural requirements, data privacy, potential for personalized medicine in AD, and limiting access to future AD treatment based on risk stratification, were covered scarcely.

CONCLUSION

The ethical discussion needs to advance to reflect recent scientific developments and guide clinical practice now and in the future, so that necessary safeguards are implemented for large-scale AD secondary prevention.

RWD-Cockpit: Application for Quality Assessment of Real-World Data (Preprint)

Background

Digital technologies are transforming the health care system. A large part of information is generated as real-world data (RWD). Data from electronic health records and digital biomarkers have the potential to reveal associations between the benefits and adverse events of medicines, establish new patient-stratification principles, expose unknown disease correlations, and inform on preventive measures. The impact for health care payers and providers, the biopharmaceutical industry, and governments is massive in terms of health outcomes, quality of care, and cost. However, a framework to assess the preliminary quality of RWD is missing, thus hindering the conduct of population-based observational studies to support regulatory decision-making and real-world evidence.

Objective

To address the need to qualify RWD, we aimed to build a web application as a tool to translate characterization of some quality parameters of RWD into a metric and propose a standard framework for evaluating the quality of the RWD.

Methods

The RWD-Cockpit systematically scores data sets based on proposed quality metrics and customizable variables chosen by the user. Sleep RWD generated de novo and publicly available data sets were used to validate the usability and applicability of the web application. The RWD quality score is based on the evaluation of 7 variables: manageability specifies access and publication status; complexity defines univariate, multivariate, and longitudinal data; sample size indicates the size of the sample or samples; privacy and liability stipulates privacy rules; accessibility specifies how the data set can be accessed and to what granularity; periodicity specifies how often the data set is updated; and standardization specifies whether the data set adheres to any specific technical or metadata standard. These variables are associated with several descriptors that define specific characteristics of the data set.

Results

To address the need to qualify RWD, we built the RWD-Cockpit web application, which proposes a framework and applies a common standard for a preliminary evaluation of RWD quality across data sets—molecular, phenotypical, and social—and proposes a standard that can be further personalized by the community retaining an internal standard. Applied to 2 different case studies—de novo–generated sleep data and publicly available data sets—the RWD-Cockpit could identify and provide researchers with variables that might increase quality.

Conclusions

The results from the application of the framework of RWD metrics implemented in the RWD-Cockpit application suggests that multiple data sets can be preliminarily evaluated in terms of quality using the proposed metrics. The output scores—quality identifiers—provide a first quality assessment for the use of RWD. Although extensive challenges remain to be addressed to set RWD quality standards, our proposal can serve as an initial blueprint for community efforts in the characterization of RWD quality for regulated settings.

Real-world evidence and product development: Opportunities, challenges and risk mitigation

Real-world evidence (RWE) is derived from real-world data (RWD) sources including electronic health records, claims data, registries (disease, product) and pragmatic clinical trials. The importance of RWE derived from RWD has been once again demonstrated during the coronavirus disease 2019 (COVID-19) pandemic, as it can improve patient care by complementing information obtained from traditional clinical trial programs. Additionally, RWE can generate insights into disease mechanisms, epidemiology, patient flows in and out of healthcare systems, and drivers and barriers to optimal clinical care in real-world settings. Identifying unmet medical needs is crucial as it often can inform which investigational new drugs enter clinical trial testing, and RWE studies from hospital settings have contributed substantial progress here. RWE can also optimize the design of clinical studies, inform benefit risk assessments and use networks of pragmatic studies to help with clinical trial feasibilities and eventual trial initiation. The challenges of RWD include data quality, reproducibility and accuracy which may affect validity. RWD and RWE must be fit for purpose and one must be cognizant of inherent biases.

Conducting public involvement in dementia research: The contribution of the European Working Group of People with Dementia to the ROADMAP project

Background

Dementia outcomes include memory loss, language impairment, reduced quality of life and personality changes. Research suggests that outcomes selected for dementia clinical trials might not be the most important to people affected.

Objective

One of the goals of the ‘Real world Outcomes across the Alzheimer's Disease spectrum for better care: Multi‐modal data Access Platform’ (ROADMAP) project was to identify important outcomes from the perspective of people with dementia and their caregivers. We review how ROADMAP's Public Involvement shaped the programme, impacted the research process and gave voice to people affected by dementia.

Design

The European Working Group of People with Dementia (EWGPWD) were invited to participate. In‐person consultations were held with people with dementia and caregivers, with advance information provided on ROADMAP activities. Constructive criticism of survey content, layout and accessibility was sought, as were views and perspectives on terminology and key concepts around disease progression.

Results

The working group provided significant improvements to survey accessibility and acceptability. They promoted better understanding of concepts around disease progression and how researchers might approach measuring and interpreting findings. They effectively expressed difficult concepts through real‐world examples.

Conclusions

The role of the EWGPWD in ROADMAP was crucial, and its impact was highly influential. Involvement from the design stage helped shape the ethos of the programme and ultimately its meaningfulness.

Public contribution

People with dementia and their carers were involved through structured consultations and invited to provide feedback on project materials, methods and insight into terminology and relevant concepts.

Estimation of the epidemiology of dementia and associated neuropsychiatric symptoms by applying machine learning to real-world data

INTRODUCTION

Incidence rates of dementia-related neuropsychiatric symptoms (NPS) are not known and this hampers the assessment of their population burden. The objective of this study was to obtain an approximate estimate of the population incidence and prevalence of both dementia and NPS.

METHODS

Given the dynamic nature of the population with dementia, a retrospective study was conducted within the database of the Basque Health Service (real-world data) at the beginning and end of 2019. Validated random forest models were used to identify separately depressive and psychotic clusters according to their presence in the electronic health records of all patients diagnosed with dementia.

RESULTS

Among the 631,949 individuals over 60 years registered, 28,563 were diagnosed with dementia, of whom 15,828 (55.4%) showed psychotic symptoms and 19,461 (68.1%) depressive symptoms. The incidence of dementia in 2019 was 6.8/1000 person-years. Most incident cases of depressive (72.3%) and psychotic (51.9%) NPS occurred in cases of incident dementia. The risk of depressive-type NPS grows with years since dementia diagnosis, living in a nursing home, and female sex, but falls with older age. In the psychotic cluster model, the effects of male sex, and older age are inverted, both increasing the probability of this type of symptoms.

CONCLUSIONS

The stigmatization factor conditions the social and attitudinal environment, delaying the diagnosis of dementia, preventing patients from receiving adequate care and exacerbating families' suffering. This study evidences the synergy between big data and real-world data for psychiatric epidemiological research.

Obtaining EQ-5D-5L utilities from the disease specific quality of life Alzheimer's disease scale: development and results from a mapping study

PURPOSE

The Quality of Life Alzheimer's Disease Scale (QoL-AD) is commonly used to assess disease specific health-related quality of life (HRQoL) as rated by patients and their carers. For cost-effectiveness analyses, utilities based on the EQ-5D are often required. We report a new mapping algorithm to obtain EQ-5D indices when only QoL-AD data are available.

METHODS

Different statistical models to estimate utility directly, or responses to individual EQ-5D questions (response mapping) from QoL-AD, were trialled for patient-rated and proxy-rated questionnaires. Model performance was assessed by root mean square error and mean absolute error.

RESULTS

The response model using multinomial regression including age and sex, performed best in both the estimation dataset and an independent dataset.

CONCLUSIONS

The recommended mapping algorithm allows researchers for the first time to estimate EQ-5D values from QoL-AD data, enabling cost-utility analyses using datasets where the QoL-AD but no utility measures were collected.

ANMerge: A Comprehensive and Accessible Alzheimer's Disease Patient-Level Dataset

BACKGROUND

Accessible datasets are of fundamental importance to the advancement of Alzheimer's disease (AD) research. The AddNeuroMed consortium conducted a longitudinal observational cohort study with the aim to discover AD biomarkers. During this study, a broad selection of data modalities was measured including clinical assessments, magnetic resonance imaging, genotyping, transcriptomic profiling, and blood plasma proteomics. Some of the collected data were shared with third-party researchers. However, this data was incomplete, erroneous, and lacking in interoperability.

OBJECTIVE

To provide the research community with an accessible, multimodal, patient-level AD cohort dataset.

METHODS

We systematically addressed several limitations of the originally shared resources and provided additional unreleased data to enhance the dataset.

RESULTS

In this work, we publish and describe ANMerge, a new version of the AddNeuroMed dataset. ANMerge includes multimodal data from 1,702 study participants and is accessible to the research community via a centralized portal.

CONCLUSION

ANMerge is an information rich patient-level data resource that can serve as a discovery and validation cohort for data-driven AD research, such as, for example, machine learning and artificial intelligence approaches.

Health-related quality of life in people with predementia Alzheimer's disease, mild cognitive impairment or dementia measured with preference-based instruments: a systematic literature review

BACKGROUND

Obtaining reliable estimates of the health-related quality of life (HR-QoL) of people with predementia Alzheimer's disease [AD] (preclinical or prodromal AD), mild cognitive impairment (MCI) and dementia is essential for economic evaluations of related health interventions.

AIMS

To provide an overview of which quality of life instruments are being used to assess HR-QoL in people with predementia AD, MCI or dementia; and, to summarise their reported HR-QoL levels at each stage of the disease and by type of respondent.

METHODS

We systematically searched for and reviewed eligible studies published between January 1990 and the end of April 2017 which reported HR-QoL for people with predementia AD, MCI or dementia. We only included instruments which are preference-based, allowing index scores/utility values to be attached to each health state they describe based on preferences obtained from population surveys. Summary results were presented by respondent type (self or proxy), type of instrument, geographical location and, where possible, stage of disease. Health state utility values derived using the EuroQoL 5-Dimensions (EQ-5D) were meta-analysed by pooling reported results across all studies by disease severity (MCI, mild, mild to moderate, moderate, severe dementia, not specified) and by respondent (person with dementia, carer, general public, not specified), using a fixed-effects approach.

RESULTS

We identified 61 studies which reported HR-QoL for people with MCI or dementia using preference-based instruments, of which 48 used the EQ-5D. Thirty-six studies reported HR-QoL for mild and/or moderate disease severities, and 12 studies reported utility values for MCI. We found systematic differences between self-rated and proxy-rated HR-QoL, with proxy-rated utility valued being significantly lower in more severe disease states.

CONCLUSIONS

A substantial literature now exists quantifying the impact of dementia on HR-QoL using preference-based measures, giving researchers and modellers a firmer basis on which to select appropriate utility values when estimating the effectiveness and cost-effectiveness of interventions in this area. Further research is required on HR-QoL of people with preclinical and prodromal AD and MCI, possible differences by type of dementia, the effects of comorbidities, study setting and the informal caregiver's own HR-QoL, including any effect of that on their proxy-ratings.

Good problems to have? Policy and societal implications of a disease-modifying therapy for presymptomatic late-onset Alzheimer's disease

In the United States alone, the prevalence of AD is expected to more than double from six million people in 2019 to nearly 14 million people in 2050. Meanwhile, the track record for developing treatments for AD has been marked by decades of failure. But recent progress in genetics, neuroscience and gene editing suggest that effective treatments could be on the horizon. The arrival of such treatments would have profound implications for the way we diagnose, triage, study, and allocate resources to Alzheimer's patients. Because the disease is not rare and because it strikes late in life, the development of therapies that are expensive and efficacious but less than cures, will pose particular challenges to healthcare infrastructure. We have a window of time during which we can begin to anticipate just, equitable and salutary ways to accommodate a disease-modifying therapy Alzheimer's disease. Here we consider the implications for caregivers, clinicians, researchers, and the US healthcare system of the availability of an expensive, presymptomatic treatment for a common late-onset neurodegenerative disease for which diagnosis can be difficult.

Real-world evidence in Alzheimer's disease: The ROADMAP Data Cube

INTRODUCTION

The ROADMAP project aimed to provide an integrated overview of European real-world data on Alzheimer's disease (AD) across the disease spectrum.

METHODS

Metadata were identified from data sources in catalogs of European AD projects. Priority outcomes for different stakeholders were identified through systematic literature review, patient and public consultations, and stakeholder surveys.

RESULTS

Information about 66 data sources and 13 outcome domains were integrated into a Data Cube. Gap analysis identified cognitive ability, functional ability/independence, behavioral/neuropsychiatric symptoms, treatment, comorbidities, and mortality as the outcomes collected most. Data were most lacking in caregiver-related outcomes. In general, electronic health records covered a broader, less detailed data spectrum than research cohorts.

DISCUSSION

This integrated real-world AD data overview provides an intuitive visual model that facilitates initial assessment and identification of gaps in relevant outcomes data to inform future prospective data collection and matching of data sources and outcomes against research protocols.

Validation of Random Forest Machine Learning Models to Predict Dementia-Related Neuropsychiatric Symptoms in Real-World Data

BACKGROUND

Neuropsychiatric symptoms (NPS) are the leading cause of the social burden of dementia but their role is underestimated.

OBJECTIVE

The objective of the study was to validate predictive models to separately identify psychotic and depressive symptoms in patients diagnosed with dementia using clinical databases representing the whole population to inform decision-makers.

METHODS

First, we searched the electronic health records of 4,003 patients with dementia to identify NPS. Second, machine learning (random forest) algorithms were applied to build separate predictive models for psychotic and depressive symptom clusters in the training set (N = 3,003). Third, calibration and discrimination were assessed in the test set (N = 1,000) to assess the performance of the models.

RESULTS

Neuropsychiatric symptoms were noted in the electronic health record of 58% of patients. The area under the receiver operating curve reached 0.80 for the psychotic cluster model and 0.74 for the depressive cluster model. The Kappa index and accuracy also showed better discrimination in the psychotic model. Calibration plots indicated that both types of model had less predictive accuracy when the probability of neuropsychiatric symptoms was <25%. The most important variables in the psychotic cluster model were use of risperidone, level of sedation, use of quetiapine and haloperidol and the number of antipsychotics prescribed. In the depressive cluster model, the most important variables were number of antidepressants prescribed, escitalopram use, level of sedation, and age.

CONCLUSION

Given their relatively good performance, the predictive models can be used to estimate prevalence of NPS in population databases.

Health Outcome Prioritization in Alzheimer's Disease: Understanding the Ethical Landscape

BACKGROUND

Dementia has been described as the greatest global health challenge in the 21st Century on account of longevity gains increasing its incidence, escalating health and social care pressures. These pressures highlight ethical, social, and political challenges about healthcare resource allocation, what health improvements matter to patients, and how they are measured. This study highlights the complexity of the ethical landscape, relating particularly to the balances that need to be struck when allocating resources; when measuring and prioritizing outcomes; and when individual preferences are sought.

OBJECTIVE

Health outcome prioritization is the ranking in order of desirability or importance of a set of disease-related objectives and their associated cost or risk. We analyze the complex ethical landscape in which this takes place in the most common dementia, Alzheimer's disease.

METHODS

Narrative review of literature published since 2007, incorporating snowball sampling where necessary. We identified, thematized, and discussed key issues of ethical salience.

RESULTS

Eight areas of ethical salience for outcome prioritization emerged: 1) Public health and distributive justice, 2) Scarcity of resources, 3) Heterogeneity and changing circumstances, 4) Knowledge of treatment, 5) Values and circumstances, 6) Conflicting priorities, 7) Communication, autonomy and caregiver issues, and 8) Disclosure of risk.

CONCLUSION

These areas highlight the difficult balance to be struck when allocating resources, when measuring and prioritizing outcomes, and when individual preferences are sought. We conclude by reflecting on how tools in social sciences and ethics can help address challenges posed by resource allocation, measuring and prioritizing outcomes, and eliciting stakeholder preferences.

I-O Optimise: a novel multinational real-world research platform in thoracic malignancies

Aim: To describe I-O Optimise, a multinational program providing real-world insights into lung cancer management. Materials & methods: Real-world data source selection for I-O Optimise followed a structured approach focused on population coverage, key variable capture, continuous/consistent data availability, record duration and data latency, and database expertise. Results: As of 31 October 2018, seven real-world data sources were included in I-O Optimise, providing data on characteristics, treatment patterns and clinical outcomes from more than 45,000 patients/year with non-small-cell lung cancer, small-cell lung cancer and mesothelioma across Denmark, Norway, Portugal, Spain, Sweden and the UK. Conclusion: The ongoing I-O Optimise initiative has the potential to provide a broad, robust and dynamic research platform to continually address numerous research objectives in the lung cancer arena.