With rapid aging of world population, Alzheimer’s disease is becoming a leading cause of death after cardiovascular disease and cancer. Nearly 10% of people who are over 65 years old are affected by Alzheimer’s disease. The causes have been studied intensively, but no definitive answer has been found. Genetic predisposition, abnormal protein deposits in brain, and environmental factors are suspected to play a role in the development of this disease. In this paper, we model progression of Alzheimer’s disease using a multi-state Markov model to investigate the significance of known risk factors such as age, apolipoprotein E4, and some brain structural volumetric variables from magnetic resonance imaging scans (e.g., hippocampus, etc.) while predicting transitions between different clinical diagnosis states. With the Alzheimer’s Disease Neuroimaging Initiative data, we found that the model with age is not significant (p = 0.1733) according to the likelihood ratio test, but the apolipoprotein E4 is a significant risk factor, and the examination of apolipoprotein E4-by-sex interaction suggests that the apolipoprotein E4 link to Alzheimer’s disease is stronger in women. Given the estimated transition probabilities, the prediction accuracy is as high as 0.7849.
MillsKLTamnesCK. Methods and considerations for longitudinal structural brain imaging analysis across development. Dev Cogn Neurosci2014; 9: 172–190.
3.
AllenJSDamasioHGrabowskiTJ. Normal neuroanatomical variation in the human brain: an MRI-volumetric study. Am J Phys Anthropol2002; 118: 341–358.
4.
RibeiroPFVentura-AntunesLGabiM, et al.The human cerebral cortex is neither one nor many: neuronal distribution reveals two quantitatively different zones in the gray matter, three in the white matter, and explains local variations in cortical folding. Front Neuroanat2013; 7: 10–3389.
5.
GiorgioADe StefanoN. Clinical use of brain volumetry. J Magn Reson Imaging2013; 37: 1–14.
6.
FrisoniGBFoxNCJackCR, et al.The clinical use of structural MRI in Alzheimer’s disease. Nat Rev Neurol2010; 6: 67–77.
7.
PetersenRCSmithGEWaringSC, et al.Mild cognitive impairment: clinical characterization and outcome. Arch Neurol1999; 56: 303–308.
8.
BouwmanFSchoonenboomSvan Der FlierW, et al.CSF biomarkers and medial temporal lobe atrophy predict dementia in mild cognitive impairment. Neurobiol Aging2007; 28: 1070–1074.
9.
DesikanRFischlBCabralH, et al.MRI measures of temporoparietal regions show differential rates of atrophy during prodromal AD. Neurology2008; 71: 819–825.
10.
LikemanMAndersonVMStevensJM, et al.Visual assessment of atrophy on magnetic resonance imaging in the diagnosis of pathologically confirmed young-onset dementias. Arch Neurol2005; 62: 1410–1415.
11.
VemuriPWisteHWeigandS, et al.MRI and CSF biomarkers in normal, MCI, and AD subjects predicting future clinical change. Neurology2009; 73: 294–301.
12.
Meira-MachadoLFde Uña-ÁlvarezJCadarso-SuárezC, et al.Multi-state models for the analysis of time-to-event data. Stat Methods Med Res2009; 18: 195–222.
13.
CommengesD. Multi-state models in epidemiology. Lifetime Data Anal1999; 5: 315–327.
14.
CommengesD. Inference for multi-state models from interval-censored data. Stat Methods Med Res2002; 11: 167–182.
15.
Sukkar R, Katz E, Zhang Y, et al. Disease progression modeling using hidden Markov models. In: Engineering in Medicine and Biology Society (EMBC), 2012 34th annual international conference of the IEEE EMBS. San Diego, USA: IEEE, pp. 2845–2848.
16.
WangYResnickSMDavatzikosC. Analysis of spatio-temporal brain imaging patterns by hidden Markov models and serial MRI images. Hum Brain Mapp2014; 35: 4777–4794.
17.
YuHYangSGaoJ, et al.Multi-state Markov model in outcome of mild cognitive impairments among community elderly residents in mainland china. Int Psychogeriatr2013; 25: 797–804.
18.
Godbey MW. The use of variable-bagging and the cross-validation selector in the prediction of Alzheimer using the ADNI database. PhD Thesis, The University of Louisville’s Institutional Repository, USA, 2014.
19.
ChenYPhamTD. Development of a brain MRI-based hidden Markov model for dementia recognition. Biomed Eng Online2013; 12: S2–S2.
20.
ZhangDShenDADNI. Predicting future clinical changes of MCI patients using longitudinal and multimodal biomarkers. PLoS One2012; 7: e33182–e33182.
21.
SchmitterDRocheAMaréchalB, et al.An evaluation of volume-based morphometry for prediction of mild cognitive impairment and Alzheimer’s disease. Neuroimage Clin2015; 7: 7–17.
22.
GaserCFrankeKKlöppelS, et al.Brainage in mild cognitive impaired patients: predicting the conversion to Alzheimer’s disease. PLoS One2013; 8: e67346–e67346.
23.
SweetingMFarewellVDe AngelisD. Multi-state Markov models for disease progression in the presence of informative examination times: an application to hepatitis c. Stat Med2010; 29: 1161–1174.
24.
GelbDJ. Measurement of progression in Alzheimer’s disease: a clinician’s perspective. Stat Med2000; 19: 1393–1400.
25.
BarnesDELeeSJ. Predicting Alzheimer’s risk: why and how?Alzheimers Res Ther2011; 3: 1–3.
26.
JostBCGrossbergGT. The natural history of Alzheimer’s disease: a brain bank study. J Am Geriatr Soc1995; 43: 1248–1255.
27.
CranePKCarleAGibbonsLE, et al.Development and assessment of a composite score for memory in the Alzheimer’s disease neuroimaging initiative (ADNI). Brain Imaging Behav2012; 6: 502–516.
28.
CedarbaumJMJarosMHernandezC, et al.Rationale for use of the clinical dementia rating sum of boxes as a primary outcome measure for Alzheimer’s disease clinical trials. Alzheimers Dement2013; 9: S45–S55.
JacksonCHSharplesLDThompsonSG, et al.Multistate Markov models for disease progression with classification error. Statistician2003; 52: 193–209.
31.
WhittW. Continuous-time Markov chains, New York: Columbia University, 2006.
32.
CommengesDJolyPLetenneurL, et al.Incidence and mortality of Alzheimer’s disease or dementia using an illness-death model. Stat Med2004; 23: 199–210.
33.
MachinDCheungYBParmarMK. Cox’s proportional hazards model. Survival analysis: a practical approach, 2nd ed. Chichester: John Wiley & Sons, 2006, pp. 121–153.
34.
NorrisJR. Markov Chains, Cambridge: Cambridge University Press, 1998.
35.
CancholaAJStewartSLBernsteinL, et al.Cox regression using different time-scales, San Francisco: Western Users of SAS Software, 2003.
36.
KomELGraubardBIMidthuneD. Time-to-event analysis of longitudinal follow-up of a survey: choice of the time-scale. Am J Epidemiol1997; 145: 72–80.
37.
JolyPCommengesDHelmerC, et al.A penalized likelihood approach for an illness–death model with interval-censored data: application to age-specific incidence of dementia. Biostatistics2002; 3: 433–443.
38.
VaradhanRXueQLBandeen-RocheK. Semicompeting risks in aging research: methods, issues and needs. Lifetime Data Anal2014; 20: 538–562.
39.
Vakulenko-LagunBMandelM. Comparing estimation approaches for the illness–death model under left truncation and right censoring. Stat Med2016; 35: 1533–1548.
40.
LeeKHRondeauVHaneuseS. Accelerated failure time models for semi-competing risks data in the presence of complex censoring. Biometrics2017; 73: 1401–1412.
41.
KleinJPMoeschbergerML. Survival analysis: techniques for censored and truncated data, New York: Springer Science & Business Media, 2005.
42.
ChalisePChickenEMcGeeD. Time scales in epidemiological analysis: an empirical comparison. Int J Stat Probab2016; 5: 91–91.
43.
ChalisePChickenEMcGeeD. Baseline age effect on parameter estimates in cox models. J Stat Comput Simul2012; 82: 1767–1774.
44.
ChalisePChickenEMcGeeD. Performance and prediction for varying survival time scales. Commun Stat Simul Comput2013; 42: 636–649.
45.
ChalisePChickenEMcGeeD. Time scales in epidemiological analysis: an empirical comparison. Int J Stat Probab2016; 5: 91–91.
46.
LamarcaRAlonsoJGomezG, et al.Left-truncated data with age as time scale: an alternative for survival analysis in the elderly population. J Gerontol A Biol Sci Med Sci1998; 53: M337–M343.
47.
LorenziMPennecXFrisoniGB, et al.Disentangling normal aging from Alzheimer’s disease in structural magnetic resonance images. Neurobiol Aging2015; 36: S42–S52.
KawasCGraySBrookmeyerR, et al.Age-specific incidence rates of Alzheimer’s disease the Baltimore longitudinal study of aging. Neurology2000; 54: 2072–2077.
50.
FjellAMMcEvoyLHollandD, et al.What is normal in normal aging? Effects of aging, amyloid and Alzheimer’s disease on the cerebral cortex and the hippocampus. Prog Neurobiol2014; 117: 20–40.
51.
SalthouseTA. Robust cognitive change. J Int Neuropsychol Soc2012; 18: 749–756.
52.
CorderESaundersAStrittmatterW, et al.Gene dose of apolipoprotein E type 4 allele and the risk of Alzheimer’s disease in late onset families. Science1993; 261: 921–923.
53.
SaundersAStrittmatterWSchmechelD, et al.Association of apolipoprotein E allele ε4 with late-onset familial and sporadic Alzheimer’s disease. Neurology1993; 43: 1467–1467.
54.
GerdesLUKlausenICSihmI, et al.Apolipoprotein E polymorphism in a Danish population compared to findings in 45 other study populations around the world. Genet Epidemiol1992; 9: 155–167.
55.
RisacherSLKimSShenL, et al.The role of apolipoprotein E (APOE) genotype in early mild cognitive impairment (E-MCI). Front Aging Neurosci2013; 5: 11–11.
56.
ShiJLeporeNGutmanBA, et al.Genetic influence of apolipoprotein E4 genotype on hippocampal morphometry: an n = 725 surface-based Alzheimer’s disease neuroimaging initiative study. Hum Brain Mapp2014; 35: 3903–3918.
57.
SpampinatoMVRumboldtZHoskerRJ, et al.Apolipoprotein E and gray matter volume loss in patients with mild cognitive impairment and Alzheimer’s disease. Radiology2011; 258: 843–852.
58.
AltmannATianLHendersonVW, et al.Sex modifies the APOE-related risk of developing Alzheimer disease. Ann Neurol2014; 75: 563–573.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
