Quantitative differential diagnostics in dementia

cNeuro cDSI is a tool for clinical decision support in dementia based on combination of imaging, lab results and clinical data.


  • Cloud-based tool running in a standard browser.
  • Comparison of patient’s data to data from previously diagnosed patients providing a quantitative estimate about patient’s similarity to different disease groups.
  • Intuitive and interactive visualization of the similarity.
  • Decision models available for etiology and progression.
  • Patient data supported: clinical and neuropsychological test data, MRI imaging biomarkers, CSF biomarkers and APOE gene.
In clinical diagnostics, the role of quantitative data acquired, e.g., from clinical and neuropsychological tests, imaging and body fluids is increasing. Interpretation of all these, sometimes contradictory, data is challenging, especially when simultaneously keeping in mind patient demographics, increasing knowledge on disease subtypes and existing economic constraints for acquiring data. cDSI helps to systemize this interpretation and make it more quantitative.


  • Cloud-based – software runs in a standard web browser.
  • Computation of disease state index measuring the similarity of the patient to previously diagnosed patients.
  • Data sources supported:
    • Clinical and neuropsychological tests: MMSE, RAVLT/CERAD recall & delayed recall, TMT A&B, Animal fluency, NPI.
    • MRI imaging biomarkers from cMRI: volumes, computed MTA, GCA (global and local), Fazekas.
    • Biomarkers: CSF biomarkers, APOE.
  • Decision models available:
    • Etiology: Alzheimer’s disease (AD), frontotemporal lobar degeneration (FTLD), vascular dementia (VaD), cognitively normal (CN).
    • Progression: stable and progressive mild cognitive impairment.
  • Compact visualization of all data using the patented disease state fingerprint technology.
Disease state fingerprint comparing FTLD and AD. Red indicative to FTLD and blue to AD.
Decision model for etiology showing the highest similarity to FTLD.
Distributions of beta amyloid CSF biomarker in AD (blue) and FTLD (red) groups and the value measured for the patient (yellow).

List of publications

  • M. Bruun et al. Impact of a clinical decision support tool on dementia diagnostics in memory clinics, The PredictND validation study. Current Alzheimer Research 16: 91-101, 2019. https://doi.org/10.2174/1567205016666190103152425
  • Rhodius-Meester et al. Computer-assisted prediction of clinical progression in the earliest stages of AD. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring (2018). https://www.sciencedirect.com/science/article/pii/S2352872918300666
  • Bruun et al. Evaluating combinations of diagnostic tests to discriminate different dementia types. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring 10, 509-518, 2018. https://doi.org/10.1016/j.dadm.2018.07.003
  • Tolonen et al. Data-driven differential diagnosis of dementia using multiclass Disease State Index. Frontiers in Aging Neuroscience 10:111, 1-11, 2018.  https://doi.org/10.3389/fnagi.2018.00111
  • Rhodius-Meester et al. Integrating biomarkers for underlying Alzheimer’s disease in mild cognitive impairment in daily practice: Comparison of a clinical decision support system with individual biomarkers. Journal of Alzheimer’s Disease 50: 261-270, 2016.
  • Hall et al. Generalizability of the Disease State Index Prediction Model for Identifying Patients Progressing from Mild Cognitive Impairment to Alzheimer’s Disease. Journal of Alzheimer’s Disease 44(1): 79-92, 2015.
  • Hall et al. Predicting Progression from Cognitive Impairment to Alzheimer’s Disease with the Disease State Index. Current Alzheimer Research, 12: 69-79, 2015.
  • Runtti el al. Quantitative evaluation of disease progression in longitudinal mild cognitive impairment cohort. Journal of Alzheimer’s Disease, 39(1): 49-61, 2014.
  • Liu et al. Predicting AD conversion: comparison between prodromal AD guidelines and computer assisted PredictAD tool. PLoSOne 8(2), e55246, 2013.
  • Muñoz-Ruiz et al. Disease state fingerprint in frontotemporal degeneration with reference to Alzheimer’s disease and mild cognitive impairment. Journal of Alzheimer’s Disease, 35(4), 727-739, 2013.
  • Mattila et al. Optimizing the diagnosis of early Alzheimer’s disease in mild cognitive impairment subjects. Journal of Alzheimer’s Disease 32: 969-979, 2012.
  • Simonsen et al. Application of the PredictAD software tool to patients with mild cognitive impairment. Dementia and Geriatric Cognitive Disorders 34: 344-450, 2012.
  • Mattila et al. Disease State Fingerprint for Evaluating the State of Alzheimer’s Disease in Patients. Journal of Alzheimer’s Disease 27: 163-176, 2011.
  • Koikkalainen and Lötjönen. Method for inferring the state of a system, U.S. Patent No. 7,840,510


All data transfer uses SSL encryption. Stored data are encrypted and anonymized.
More information is available in a separate security statement.

System Requirements

Supported web browsers:

  • Google Chrome 61 or later
  • Firefox 56 or later
  • Internet Explorer 11 or later.

Recommended display resolution 1680 x 1050 or higher.

Regulatory Compliance

This product complies with European Council Directive 93/42/EEC concerning medical devices. For the US, this product is excluded from the definition of a device based on section 520(o)(1)(E) of the Food Drug and Cosmetic Act.

Indications for Use

cNeuro® cDSI is intended for use by health care professionals to aid in diagnosing patients with a suspected neurodegenerative disorder. Patient parameters and test results are entered manually by the healthcare practitioner or retrieved through integration with other hospital systems. The device suggests whether the patient’s condition meets the definition of different neurodegenerative disorders through a comparison of the patient’s data with data from patients previously diagnosed based on established guidelines. The software is intended for the purpose of enabling healthcare professionals to independently review the basis for such recommendations. It is not the intent that the healthcare professional relies primarily on the software’s recommendations to make a clinical diagnosis or treatment decision regarding an individual patient. Patient data may include biomarkers from cerebrospinal fluid and imaging, as well as results from various neuropsychological and clinical tests. The intended user profile covers healthcare professionals who work with patients being evaluated for a suspected neurodegenerative disease. The intended operational environment is an office-like environment with a computer.