Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2023 Oct 14;15(1):176.
doi: 10.1186/s13195-023-01304-8.

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

Kevin Blanco  1 , Stefanny Salcidua  2   3 , Paulina Orellana  1   2 , Tania Sauma-Pérez  2 , Tomás León  4   5 , Lorena Cecilia López Steinmetz  2   6   7 , Agustín Ibañez  2   4   8   9 , Claudia Duran-Aniotz  10   11 , Rolando de la Cruz  12   13   14
Affiliations
Review

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

Kevin Blanco et al. Alzheimers Res Ther. .

Abstract

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.

Keywords: Alzheimer’s disease; Artificial intelligence; Fluid biomarker; Machine learning; Mild cognitive impairment.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Systematic literature search flow diagram (PRISMA). This diagram starts with the total number of records identified through database searching. From there, the diagram outlines the number of records screened. Then, it indicates the number of records excluded after the initial screening, typically because the titles or abstracts clearly indicate that the studies do not meet the inclusion criteria. Next, the diagram shows the number of full-text articles assessed for eligibility, followed by the number of full-text articles excluded and the reasons for their exclusion. Finally, the diagram presents the number of studies included. This process makes the selection process transparent, which is crucial for the credibility of the systematic review
Fig. 2
Fig. 2
Supervised machine learning (ML) process. The first step is when biomarkers are taken from a cohort, then the data is pre-processed, outliers are removed, data is imputed and normalized, then the data is divided between testing and training data sets; the first is used to train the algorithms, and the second test it and validate it, if the model is selected as the best performing algorithm. Finally, the model can be used to diagnose a new patient
Fig. 3
Fig. 3
Funnel plot of algorithm performance by study. This funnel plot is a specialized form of the scatterplot, uniquely tailored for the analysis and visualization of data behavior between minimal and maximum metrics. Its primary function is to assist in identifying anomalies or outliers within the data set. In a funnel plot, data points are depicted as dots and plotted within a funnel-shaped graphical field. The shape of the funnel serves as a visual guideline, delineating the expected range of variation based on statistical norms. Consequently, any data point, or dot, that is plotted outside this funnel shape is classified as an outlier, indicating a substantial deviation from the anticipated pattern or range. In the context of this review, it is noteworthy that all the metrics derived from the studies are plotted within the confines of the funnel. This suggests that there is a consistent pattern in the data, with no significant anomalies or outliers detected. It implies that the metrics of the studies fall within the expected range and adhere to the statistical norms, reinforcing the reliability and validity of the reviewed studies
Fig. 4
Fig. 4
Scatterplot of algorithm performance. Scatterplot representing the performance of the ML algorithms. The x-axis, labeled “ACC,” measures the accuracy of the algorithms. Accuracy is a simple metric for binary classification problems, representing the proportion of true results (both true positives and true negatives) among the total number of cases examined. The y-axis, labeled “AUC,” represents the area under the receiver operating characteristic (ROC) curve. AUC is a popular metric in machine learning for binary classification problems. It measures the tradeoff between a true-positive rate and a false-positive rate. An AUC of 1.0 means the model has a perfect classification, while an AUC of 0.5 implies the model is no better than random guessing. Each point in the scatterplot represents a different machine learning algorithm. The position of the point on the graph shows the performance of the algorithm on both metrics: its accuracy and its AUC score. The scatterplot also features a performance target of 0.8. This could be represented as a line or a highlighted area in the plot, indicating the desired minimum performance level for both the accuracy and AUC. Algorithms that fall within or above this target region are considered to meet or exceed the performance goal. This visual comparison makes it easier to quickly identify which algorithms meet the performance target according to these two key metrics
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Winblad B, Palmer K, Kivipelto M, Jelic V, Fratiglioni L, Wahlund LO, Nordberg A, Bäckman L, Albert M, Almkvist O, Arai H, Basun H, Blennow K, de Leon M, DeCarli C, Erkinjuntti T, Giacobini E, Graff C, Hardy J, Jack C, et al. Mild cognitive impairment–beyond controversies, towards a consensus: report of the International Working Group on Mild Cognitive Impairment. J Internal Med. 2004;256(3):240–246. - PubMed
    1. Sachdev PS, Lipnicki DM, Kochan NA, Crawford JD, Thalamuthu A, Andrews G, Brayne C, Matthews FE, Stephan BC, Lipton RB, Katz MJ, Ritchie K, Carrière I, Ancelin ML, Lam LC, Wong CH, Fung AW, Guaita A, Vaccaro R, Davin A, et al. Cohort Studies of Memory in an International Consortium (COSMIC). The prevalence of mild cognitive impairment in diverse geographical and ethnocultural regions: the COSMIC Collaboration. PLoS ONE. 2015;10(11):e0142388. - PMC - PubMed
    1. Livingston G, Sommerlad A, Orgeta V, Costafreda SG, Huntley J, Ames D, Ballard C, Banerjee S, Burns A, Cohen-Mansfield J, Cooper C, Fox N, Gitlin LN, Howard R, Kales HC, Larson EB, Ritchie K, Rockwood K, Sampson EL, Samus Q, et al. Dementia prevention, intervention, and care. Lancet (London, England). 2017;390(10113):2673–2734. - PubMed
    1. Hulette CM, Welsh-Bohmer KA, Murray MG, Saunders AM, Mash DC, McIntyre LM. Neuropathological and neuropsychological changes in “normal” aging: evidence for preclinical Alzheimer disease in cognitively normal individuals. J Neuropathol Exp Neurol. 1998;57(12):1168–1174. - PubMed
    1. Grill JD, Raman R, Ernstrom K, Aisen P, Karlawish J. Effect of study partner on the conduct of Alzheimer disease clinical trials. Neurology. 2013;80(3):282–288. - PMC - PubMed

Publication types

MeSH terms

-