Computational Neurology: Computational Modeling Approaches in Dementia

Liu

IEEE J. Biomed. Health Inform.

et al. 2022

Self Cite

Accurate computational models for clinical decision support systems require clean and reliable data but, in clinical practice, data are often incomplete. Hence, missing data could arise not only from training datasets but also test datasets which could consist of a single undiagnosed case, an individual. This work addresses the problem of extreme missingness in both training and test data by evaluating multiple imputation and classification workflows based on both diagnostic classification accuracy and computational cost. Extreme missingness is defined as having ~50% of the total data missing in more than half the data features. In particular, we focus on dementia diagnosis due to long time delays, high variability, high attrition rates and lack of practical data imputation strategies in its diagnostic pathway. We identified and replicated the extreme missingness structure of data from a real-world memory clinic on a larger open dataset, with the original complete data acting as ground truth. Overall, we found that computational cost, but not accuracy, varies widely for various imputation and classification approaches. Particularly, we found that iterative imputation on the training dataset combined with a reduced-feature classification model provides the best approach, in terms of speed and accuracy. Taken together, this work has elucidated important factors to be considered when developing a predictive model for a dementia diagnostic support system.

Section: ) Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Practical Strategies for Extreme Missing Data Imputation in Dementia Diagnosis

Liu

IEEE J. Biomed. Health Inform.

et al. 2022

Self Cite

“…The use of machine learning approaches in dementia research has been facilitated by openly available dementia datasets [4] . They often include a wide range of dementia assessments, including CFAs, with large sample size, thus providing a rich data source to develop and apply machine learning techniques towards improving dementia diagnosis and prognosis [14] , [15] . In particular, with the large number of variables in these open datasets, and in clinical datasets, a frequently employed machine learning approach is feature selection [16] , which seeks to identify which variables (features) are relatively more useful for building a computational (e.g.…”

Section: Introductionmentioning

confidence: 99%

Alzheimer’s Disease Assessments Optimized for Diagnostic Accuracy and Administration Time

IEEE J. Transl. Eng. Health Med.

Prasad

et al. 2022

Self Cite

Objective: Despite the potential of machine learning techniques to improve dementia diagnostic processes, research outcomes are often not readily translated to or adopted in clinical practice. Importantly, the time taken to administer diagnostic assessment has yet to be taken into account in feature-selection based optimisation for dementia diagnosis. We address these issues by considering the impact of assessment time as a practical constraint for feature selection of cognitive and functional assessments in Alzheimer’s disease diagnosis. Methods: We use three different feature selection algorithms to select informative subsets of dementia assessment items from a large open-source dementia dataset. We use cost-sensitive feature selection to optimise our feature selection results for assessment time as well as diagnostic accuracy. To encourage clinical adoption and further evaluation of our proposed accuracy-vs-cost optimisation algorithms, we also implement a sandbox-like toolbox with graphical user interface to evaluate user-chosen subsets of assessment items. Results: We find that there are subsets of accuracy-cost optimised assessment items that can perform better in terms of diagnostic accuracy and/or total assessment time than most other standard assessments. Discussion: Overall, our analysis and accompanying sandbox tool can facilitate clinical users and other stakeholders to apply their own domain knowledge to analyse and decide which dementia diagnostic assessment items are useful, and aid the redesigning of dementia diagnostic assessments. Clinical Impact (Clinical Research): By optimising diagnostic accuracy and assessment time, we redesign predictive and efficient dementia diagnostic assessments and develop a sandbox interface to facilitate evaluation and testing by clinicians and non-specialists.

Alzheimer’s Disease Assessments Optimised for Diagnostic Accuracy and Administration Time

Prasad

et al. 2021

Preprint

Self Cite

Objective: Despite the potential of machine learning techniques to improve dementia diagnostic processes, research outcomes are often not readily translated to or adopted in clinical practice. Importantly, the cost of assessment items, in terms of assessment time, has yet to be taken into account in feature-selection based optimisation for dementia diagnosis. We address these issues by considering the impact of assessment time as a practical constraint for feature selection of cognitive and functional assessments in Alzheimer's disease diagnosis. Methods: We use three different feature selection algorithms to select informative subsets of dementia assessment items from a large open source dementia dataset. We use cost cost-sensitive feature selection to optimise our feature selection results for assessment time as well as accuracy. To encourage the clinical adoption and further evaluation of our proposed accuracy-vs-time optimisation algorithms, we also implement a sandbox-like toolbox with graphical user interface to evaluate user-chosen subsets of assessment items. Results: We find that there are subsets of accuracy-time optimised assessment items that can perform better in terms of diagnostic accuracy and/or total assessment time than most other standard assessments. Discussion: Overall, the cost-benefit optimisation analysis and accompanying sandbox tool can facilitate clinical users and other stakeholders to apply their own domain knowledge to analyse and decide which dementia diagnostic assessment items are useful, and aid the redesigning of dementia diagnostic assessments. Clinical Impact (Clinical Research): By optimising diagnostic accuracy and assessment time, we redesign predictive and efficient dementia diagnostic assessments and develop a sandbox interface to facilitate evaluation and testing by clinicians and non-specialists.