Authors: Pekkala, Timo | Hall, Anette | Lötjönen, Jyrki | Mattila, Jussi | Soininen, Hilkka | Ngandu, Tiia | Laatikainen, Tiina | Kivipelto, Miia | Solomon, Alina
Article Type: Research Article
Abstract: Background and objective: This study aimed to develop a late-life dementia prediction model using a novel validated supervised machine learning method, the Disease State Index (DSI), in the Finnish population-based CAIDE study. Methods: The CAIDE study was based on previous population-based midlife surveys. CAIDE participants were re-examined twice in late-life, and the first late-life re-examination was used as baseline for the present study. The main study population included 709 cognitively normal subjects at first re-examination who returned to the second re-examination up to 10 years later (incident dementia n = 39). An extended population (n = 1009, incident dementia 151) included non-participants/non-survivors …(national registers data). DSI was used to develop a dementia index based on first re-examination assessments. Performance in predicting dementia was assessed as area under the ROC curve (AUC). Results: AUCs for DSI were 0.79 and 0.75 for main and extended populations. Included predictors were cognition, vascular factors, age, subjective memory complaints, and APOE genotype. Conclusion: The supervised machine learning method performed well in identifying comprehensive profiles for predicting dementia development up to 10 years later. DSI could thus be useful for identifying individuals who are most at risk and may benefit from dementia prevention interventions. Show more
Keywords: Computer-assisted decision making, dementia, prediction, prevention, supervised machine learning
DOI: 10.3233/JAD-160560
Citation: Journal of Alzheimer's Disease, vol. 55, no. 3, pp. 1055-1067, 2017
Authors: Suhonen, Noora-Maria | Hallikainen, Ilona | Hänninen, Tuomo | Jokelainen, Jari | Krüger, Johanna | Hall, Anette | Pikkarainen, Maria | Soininen, Hilkka | Remes, Anne M.
Article Type: Research Article
Abstract: While behavioral symptoms are both early and prevalent features of behavioral variant frontotemporal dementia (bvFTD), they can be present in other types of dementia as well, including Alzheimer’s disease (AD) and even mild cognitive impairment (MCI). The Frontal Behavioral Inventory (FBI) was specifically developed to capture the behavioral and personality changes in bvFTD; it has also been modified into a self-administered caregiver questionnaire (FBI-mod). We examined the utility of the FBI-mod in differentiating bvFTD (n = 26), primary progressive aphasia (PPA) (n = 7), AD (n = 53), and MCI (n = 50) patients, and investigated how the FBI-mod may be associated with neuropsychological …measures. The bvFTD patients scored significantly higher as compared to all other patient groups on the FBI-mod Total (p < 0.005), Negative (p < 0.005), and Positive (p < 0.01) scores. The cut-off point for the FBI-mod Total score that best discriminated the bvFTD and AD patients in our sample was 16, thus substantially lower than reported for the original FBI. For the bvFTD group, only mild correlations emerged between the FBI-mod and the cognitive measures. However, significant correlations between the FBI-mod and depressive symptoms as measured by the BDI-II were found for bvFTD. This suggests that while behavioral symptoms appear independent from cognitive deficits in bvFTD, they may nevertheless be interrelated with depressive symptoms. We conclude that the FBI-mod is an easily administered behavioral scale that can aid in differential diagnosis of bvFTD and should be used in clinical practice. The FBI-mod may further be considered as an outcome measure in clinical trials. Show more
Keywords: Behavioral rating scale, behavioral symptoms, dementia, depressive symptoms, frontotemporal dementia, neuropsychological tests
DOI: 10.3233/JAD-160983
Citation: Journal of Alzheimer's Disease, vol. 56, no. 4, pp. 1241-1251, 2017
Authors: Muñoz-Ruiz, Miguel Ángel | Hartikainen, Päivi | Hall, Anette | Mattila, Jussi | Koikkalainen, Juha | Herukka, Sanna-Kaisa | Julkunen, Valtteri | Vanninen, Ritva | Liu, Yawu | Lötjönen, Jyrki | Soininen, Hilkka
Article Type: Research Article
Abstract: Background: Disease State Index and Disease State Fingerprint represent a novel tool which collates data information from different sources, helping the clinician in the diagnosis and follow-up of dementia diseases. It has been demonstrated that it is applicable in the diagnosis of Alzheimer’s disease (AD). Objective: We applied this novel tool to classify frontotemporal dementia (FTD) cases in comparison with controls, AD, and mild cognitive impairment (MCI) subjects. Methods: Thirty seven patients with FTD, 35 patients with AD, 26 control subjects, and 64 subjects with MCI were included in the study. The Disease State Index encompassed data from cognitive performance …assessed by Mini-Mental State Examination, cerebrospinal fluid biomarkers, MRI volumetric and morphometric parameters as well as APOE genotype. Results: We applied the Disease State Index for comparisons at the group level. The data showed that FTD patients could be differentiated with a high accuracy, sensitivity, and specificity from controls (0.84, 0.84, 0.83) and from MCI (0.79, 0.78, 0.80). However, the correct accuracy was lower in the FTD versus AD comparison (0.69, 0.70, 0.71). In addition, we demonstrated the use of Disease State Fingerprint by comparing one particular FTD case with control, AD, and MCI population data. Conclusion: The results suggest that the Disease State Fingerprint and the underlying Disease State Index are particularly useful in differentiating between normal status and disease in patients with dementia, but it may also help to distinguish between the two dementia diseases, FTD and AD. Show more
Keywords: Alzheimer's disease, cognition, frontotemporal dementia, memory, mild cognitive impairment
DOI: 10.3233/JAD-122260
Citation: Journal of Alzheimer's Disease, vol. 35, no. 4, pp. 727-739, 2013
Authors: Pekkala, Timo | Hall, Anette | Mangialasche, Francesca | Kemppainen, Nina | Mecocci, Patrizia | Ngandu, Tiia | Rinne, Juha O. | Soininen, Hilkka | Tuomilehto, Jaakko | Kivipelto, Miia | Solomon, Alina
Article Type: Short Communication
Abstract: We explored the association of type 2 diabetes related blood markers with brain amyloid accumulation on PiB-PET scans in 41 participants from the FINGER PET sub-study. We built logistic regression models for brain amyloid status with12 plasma markers of glucose and lipid metabolism, controlled for diabetes and APOE ɛ 4 carrier status. Lower levels of insulin, insulin resistance index (HOMA-IR), C-peptide, and plasminogen activator (PAI-1) were associated with amyloid positive status, although the results were not significant after adjusting for multiple testing. None of the models found evidence for associations between amyloid status and fasting glucose or HbA1c.
Keywords: Amyloid-β, apolipoprotein E, plasminogen activator, positron emission tomography, type 2 diabetes
DOI: 10.3233/JAD-200145
Citation: Journal of Alzheimer's Disease, vol. 76, no. 4, pp. 1243-1248, 2020
Authors: Jääskeläinen, Olli | Solje, Eino | Hall, Anette | Katisko, Kasper | Korhonen, Ville | Tiainen, Mika | Kangas, Antti J. | Helisalmi, Seppo | Pikkarainen, Maria | Koivisto, Anne | Hartikainen, Päivi | Hiltunen, Mikko | Ala-Korpela, Mika | Soininen, Hilkka | Soininen, Pasi | Haapasalo, Annakaisa | Remes, Anne M. | Herukka, Sanna-Kaisa
Article Type: Research Article
Abstract: Decreased levels of serum high-density lipoprotein (HDL) cholesterol have previously been linked to systemic inflammation and neurodegenerative diseases, such as Alzheimer’s disease. Here, we aimed to analyze the lipoprotein profile and inflammatory indicators, the high-sensitivity C-reactive peptide (hs-CRP) and glycoprotein acetyls (GlycA), in sporadic and C9orf72 repeat expansion-associated frontotemporal lobar degeneration (FTLD) patients. The C9orf72 hexanucleotide repeat expansion is the most frequent genetic etiology underlying FTLD. The concentrations of different lipid measures in the sera of 67 FTLD patients (15 C9orf72 repeat expansion carriers), including GlycA, were analyzed by nuclear magnetic resonance spectroscopy. To verify the state of systemic inflammation, …hs-CRP was also quantified from patient sera. We found that the total serum HDL concentration was decreased in C9orf72 repeat expansion carriers when compared to non-carriers. Moreover, decreased concentrations of HDL particles of different sizes and subclass were consistently observed. No differences were detected in the very low- and low-density lipoprotein subclasses between the C9orf72 repeat expansion carriers and non-carriers. Furthermore, hs-CRP and GlycA levels did not differ between the C9orf72 repeat expansion carriers and non-carriers. In conclusion, the HDL-related changes were linked with C9orf72 repeat expansion associated FTLD but were not seen to associate with systemic inflammation. The underlying reason for the HDL changes remains unclear. Show more
Keywords: C9orf72 protein, cholesterol, frontotemporal dementia, frontotemporal lobar degeneration, inflammation, lipoproteins
DOI: 10.3233/JAD-190132
Citation: Journal of Alzheimer's Disease, vol. 72, no. 1, pp. 127-137, 2019
Authors: Jääskeläinen, Olli | Hall, Anette | Tiainen, Mika | van Gils, Mark | Lötjönen, Jyrki | Kangas, Antti J. | Helisalmi, Seppo | Pikkarainen, Maria | Hallikainen, Merja | Koivisto, Anne | Hartikainen, Päivi | Hiltunen, Mikko | Ala-Korpela, Mika | Soininen, Pasi | Soininen, Hilkka | Herukka, Sanna-Kaisa
Article Type: Research Article
Abstract: Accurate differentiation between neurodegenerative diseases is developing quickly and has reached an effective level in disease recognition. However, there has been less focus on effectively distinguishing the prodromal state from later dementia stages due to a lack of suitable biomarkers. We utilized the Disease State Index (DSI) machine learning classifier to see how well quantified metabolomics data compares to clinically used cerebrospinal fluid (CSF) biomarkers of Alzheimer’s disease (AD). The metabolic profiles were quantified for 498 serum and CSF samples using proton nuclear magnetic resonance spectroscopy. The patient cohorts in this study were dementia (with a clinical AD diagnosis) (N = 359), …mild cognitive impairment (MCI) (N = 96), and control patients with subjective memory complaints (N = 43). DSI classification was conducted for MCI (N = 51) and dementia (N = 214) patients with low CSF amyloid-β levels indicating AD pathology and controls without such amyloid pathology (N = 36). We saw that the conventional CSF markers of AD were better at classifying controls from both dementia and MCI patients. However, quantified metabolic subclasses were more effective in classifying MCI from dementia. Our results show the consistent effectiveness of traditional CSF biomarkers in AD diagnostics. However, these markers are relatively ineffective in differentiating between MCI and the dementia stage, where the quantified metabolomics data provided significant benefit. Show more
Keywords: Alzheimer’s disease, cognitive dysfunction, dementia, machine learning, metabolomics
DOI: 10.3233/JAD-191226
Citation: Journal of Alzheimer's Disease, vol. 74, no. 1, pp. 277-286, 2020
Authors: Hall, Anette | Muñoz-Ruiz, Miguel | Mattila, Jussi | Koikkalainen, Juha | Tsolaki, Magda | Mecocci, Patrizia | Kloszewska, Iwona | Vellas, Bruno | Lovestone, Simon | Visser, Pieter Jelle | Lötjonen, Jyrki | Soininen, Hilkka | for the Alzheimer Disease Neuroimaging Initiative | the AddNeuroMed consortium, DESCRIPA and Kuopio L-MCI
Article Type: Research Article
Abstract: Background: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease. Objectives: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study. Methods: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 × 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 …subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF). Results: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results. Conclusions: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar. Show more
Keywords: Alzheimer's disease, computer-assisted diagnosis, dementia, magnetic resonance imaging (MRI), mild cognitive impairment
DOI: 10.3233/JAD-140942
Citation: Journal of Alzheimer's Disease, vol. 44, no. 1, pp. 79-92, 2015
Authors: Luikku, Antti J. | Hall, Anette | Nerg, Ossi | Koivisto, Anne M. | Hiltunen, Mikko | Helisalmi, Seppo | Herukka, Sanna-Kaisa | Junkkari, Antti | Sutela, Anna | Kojoukhova, Maria | Korhonen, Ville | Mattila, Jussi | Lötjönen, Jyrki | Rummukainen, Jaana | Alafuzoff, Irina | Jääskeläinen, Juha E. | Remes, Anne M. | Solomon, Alina | Kivipelto, Miia | Soininen, Hilkka | Rauramaa, Tuomas | Leinonen, Ville
Article Type: Research Article
Abstract: Background: Idiopathic normal pressure hydrocephalus (iNPH) patients often develop Alzheimer’s disease (AD) related brain pathology. Disease State Index (DSI) is a method to combine data from various sources for differential diagnosis and progression of neurodegenerative disorders. Objective: To apply DSI to predict clinical AD in shunted iNPH-patients in a defined population. Methods: 335 shunted iNPH-patients (median 74 years) were followed until death (n = 185) or 6/2015 (n = 150). DSI model (including symptom profile, onset age of NPH symptoms, atrophy of medial temporal lobe in CT/MRI, cortical brain biopsy finding, and APOE genotype) was applied. Performance of DSI model was evaluated …with receiver operating characteristic (ROC) curve analysis. Results: A total of 70 (21%) patients developed clinical AD during median follow-up of 5.3 years. DSI-model predicted clinical AD with moderate effectiveness (AUC = 0.75). Significant factors were cortical biopsy (0.69), clinical symptoms (0.66), and medial temporal lobe atrophy (0.66). Conclusion: We found increased occurrence of clinical AD in previously shunted iNPH patients as compared with general population. DSI supported the prediction of AD. Cortical biopsy during shunt insertion seems indicated for earlier diagnosis of comorbid AD. Show more
Keywords: Alzheimer’s disease, computer-assisted diagnosis, normal pressure hydrocephalus, Data and results has been partly presented as an abstract at Hydrocephalus 2017, Kobe, Japan
DOI: 10.3233/JAD-190334
Citation: Journal of Alzheimer's Disease, vol. 71, no. 4, pp. 1233-1243, 2019
Authors: Reijs, Babette L.R. | Vos, Stephanie J.B. | Soininen, Hilkka | Lötjonen, Jyrki | Koikkalainen, Juha | Pikkarainen, Maria | Hall, Anette | Vanninen, Ritva | Liu, Yawu | Herukka, Sanna-Kaisa | Freund-Levi, Yvonne | Frisoni, Giovanni B. | Frölich, Lutz | Nobili, Flavio | Rikkert, Marcel Olde | Spiru, Luiza | Tsolaki, Magda | Wallin, Åsa K. | Scheltens, Philip | Verhey, Frans | Visser, Pieter Jelle
Article Type: Research Article
Abstract: Background: Lifestyle factors have been associated with the risk of dementia, but the association with Alzheimer’s disease (AD) remains unclear. Objective: To examine the association between later life lifestyle factors and AD biomarkers (i.e., amyloid-β 1–42 (Aβ42 ) and tau in cerebrospinal fluid (CSF), and hippocampal volume) in individuals with subjective cognitive decline (SCD) and mild cognitive impairment (MCI). In addition, to examine the effect of later life lifestyle factors on developing AD-type dementia in individuals with MCI. Methods: We selected individuals with SCD (n = 111) and MCI (n = 353) from the DESCRIPA and Kuopio Longitudinal MCI studies. CSF Aβ42 …and tau concentrations were assessed with ELISA assay and hippocampal volume with multi-atlas segmentation. Lifestyle was assessed by clinical interview at baseline for: social activity, physical activity, cognitive activity, smoking, alcohol consumption, and sleep. We performed logistic and Cox regression analyses adjusted for study site, age, gender, education, and diagnosis. Prediction for AD-type dementia was performed in individuals with MCI only. Results: Later life lifestyle factors were not associated with AD biomarkers or with conversion to AD-type dementia. AD biomarkers were strongly associated with conversion to AD-type dementia, but these relations were not modulated by lifestyle factors. Apolipoprotein E (APOE) genotype did not influence the results. Conclusions: Later life lifestyle factors had no impact on key AD biomarkers in individuals with SCD and MCI or on conversion to AD-type dementia in MCI. Show more
Keywords: Alcohol consumption, Alzheimer’s disease, amyloid-β (1–42), cerebrospinal fluid, cognitive reserve, exercise, hippocampus, lifestyle, mild cognitive impairment
DOI: 10.3233/JAD-170039
Citation: Journal of Alzheimer's Disease, vol. 60, no. 4, pp. 1387-1395, 2017
Authors: Martiskainen, Henna | Helisalmi, Seppo | Viswanathan, Jayashree | Kurki, Mitja | Hall, Anette | Herukka, Sanna-Kaisa | Sarajärvi, Timo | Natunen, Teemu | Kurkinen, Kaisa M.A. | Huovinen, Jaakko | Mäkinen, Petra | Laitinen, Marjo | Koivisto, Anne M. | Mattila, Kari M. | Lehtimäki, Terho | Remes, Anne M. | Leinonen, Ville | Haapasalo, Annakaisa | Soininen, Hilkka | Hiltunen, Mikko
Article Type: Research Article
Abstract: Background: Several risk loci for Alzheimer's disease (AD) have been identified during recent years in large-scale genome-wide association studies. However, little is known about the mechanisms by which these loci influence AD pathogenesis. Objective: To investigate the individual and combined risk effects of the newly identified AD loci. Methods: Association of 12 AD risk loci with AD and AD-related cerebrospinal fluid (CSF) biomarkers was assessed. Furthermore, a polygenic risk score combining the effect sizes of the top 22 risk loci in AD was calculated for each individual among the clinical and neuropathological cohorts. Effects of individual risk loci and polygenic …risk scores were assessed in relation to CSF biomarker levels as well as neurofibrillary pathology and different biochemical measures related to AD pathogenesis obtained from the temporal cortex. Results: Polygenic risk scores associated with CSF amyloid-β42 (Aβ42 ) levels in the clinical cohort, and with soluble Aβ42 levels and γ-secretase activity in the neuropathological cohort. The γ-secretase effect was independent of APOE. APOE-ε4 associated with CSF Aβ42 (p < 0.001) levels. For the other risk loci, no significant associations with AD risk or CSF biomarkers were detected after multiple testing correction. Conclusions: AD risk loci polygenically contribute to Aβ pathology in the CSF and temporal cortex, and this effect is potentially associated with increased γ-secretase activity. Show more
Keywords: Alzheimer's disease, amyloid-β peptide, biomarker, cerebrospinal fluid, polygenic risk score, risk gene, tau protein
DOI: 10.3233/JAD-140777
Citation: Journal of Alzheimer's Disease, vol. 43, no. 2, pp. 565-573, 2015