Optimizing data collection for public health decisions: a data mining approach

Systematic review: fluid biomarkers and machine learning methods to improve the diagnosis from mild cognitive impairment to Alzheimer's disease

Mild cognitive impairment (MCI) is often considered an early stage of dementia, with estimated rates of progression to dementia up to 80-90% after approximately 6 years from the initial diagnosis. Diagnosis of cognitive impairment in dementia is typically based on clinical evaluation, neuropsychological assessments, cerebrospinal fluid (CSF) biomarkers, and neuroimaging. The main goal of diagnosing MCI is to determine its cause, particularly whether it is due to Alzheimer's disease (AD). However, only a limited percentage of the population has access to etiological confirmation, which has led to the emergence of peripheral fluid biomarkers as a diagnostic tool for dementias, including MCI due to AD. Recent advances in biofluid assays have enabled the use of sophisticated statistical models and multimodal machine learning (ML) algorithms for the diagnosis of MCI based on fluid biomarkers from CSF, peripheral blood, and saliva, among others. This approach has shown promise for identifying specific causes of MCI, including AD. After a PRISMA analysis, 29 articles revealed a trend towards using multimodal algorithms that incorporate additional biomarkers such as neuroimaging, neuropsychological tests, and genetic information. Particularly, neuroimaging is commonly used in conjunction with fluid biomarkers for both cross-sectional and longitudinal studies. Our systematic review suggests that cost-effective longitudinal multimodal monitoring data, representative of diverse cultural populations and utilizing white-box ML algorithms, could be a valuable contribution to the development of diagnostic models for AD due to MCI. Clinical assessment and biomarkers, together with ML techniques, could prove pivotal in improving diagnostic tools for MCI due to AD.

Modified ground-truthing: an accurate and cost-effective food environment validation method for town and rural areas

Background

A major concern in food environment research is the lack of accuracy in commercial business listings of food stores, which are convenient and commonly used. Accuracy concerns may be particularly pronounced in rural areas. Ground-truthing or on-site verification has been deemed the necessary standard to validate business listings, but researchers perceive this process to be costly and time-consuming. This study calculated the accuracy and cost of ground-truthing three town/rural areas in Minnesota, USA (an area of 564 miles, or 908 km), and simulated a modified validation process to increase efficiency without comprising accuracy. For traditional ground-truthing, all streets in the study area were driven, while the route and geographic coordinates of food stores were recorded.

Results

The process required 1510 miles (2430 km) of driving and 114 staff hours. The ground-truthed list of stores was compared with commercial business listings, which had an average positive predictive value (PPV) of 0.57 and sensitivity of 0.62 across the three sites. Using observations from the field, a modified process was proposed in which only the streets located within central commercial clusters (the 1/8 mile or 200 m buffer around any cluster of 2 stores) would be validated. Modified ground-truthing would have yielded an estimated PPV of 1.00 and sensitivity of 0.95, and would have resulted in a reduction in approximately 88 % of the mileage costs.

Conclusions

We conclude that ground-truthing is necessary in town/rural settings. The modified ground-truthing process, with excellent accuracy at a fraction of the costs, suggests a new standard and warrants further evaluation.