Get help now — free helplines

You can call any of these for free. You do not need a diagnosis, an appointment, or a crisis to call — questions and plain exhaustion are reasons enough.

  • Alzheimer's Association 24/7 Helpline 800-272-3900 24 hours a day, 365 days a year Free, confidential support and information for people with dementia, caregivers, families and the public. Master's-level clinicians. Also Spanish.
  • 988 Suicide & Crisis Lifeline 988 24/7 Call or text 988, or chat at 988lifeline.org. For anyone in emotional distress or a mental-health crisis, including caregivers.
  • Alzheimer's Foundation of America (AFA) Helpline 866-232-8484 9:00 am - 9:00 pm ET, seven days a week Licensed social workers providing support, info and referrals. Also text message and web chat. Text: 646-586-5283

In a medical emergency, call 911. More numbers, and what each line does, on the help page.

Figures are derived from ADNI data under a Data Use Agreement. Only aggregate statistics are published; no individual participant records are shown.

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is funded by the National Institute on Aging and contributions. This page is not endorsed by ADNI or the National Institute on Aging.

Cognitive tests are the cheapest measurement in the whole cohort. They need a table, a pencil and an hour, not a lumbar puncture or a PET scanner. This page asks how much they add to a model that predicts who will convert from mild cognitive impairment to dementia. Discrimination is measured with Harrell's C, where 0.5 is chance and 1.0 is perfect.

Before and after adding cognition

Harrell's C Without cognitive scores 0.635; With cognitive scores 0.847 0.5 0.6 0.7 0.8 0.9 1.0 0.5 = chance Without cognitive scores 0.635 With cognitive scores 0.847

Harrell's C for the conversion model without and with baseline cognitive scores.

What this means

The gain of 0.213 is the largest single improvement in any of the ADNI models on this site. Its 95% CI runs from 0.163 to 0.267, so even the low end is a clear improvement.

The second number is the one that matters for practice. The multimodal model already holds CSF, MRI and amyloid PET. Put baseline cognition on top of all of that and C still rises by 0.057. Cognitive scores carry information the biomarkers do not, and the reverse is also true: the biomarkers are not made redundant by the tests.

Read these caveats first

  1. Part of this is circular. A diagnosis of dementia rests partly on cognitive and functional decline. A low baseline score predicts conversion partly because the person is already further along the same path the outcome measures.
  2. Timing, not cause. Cognitive scores tell you where someone is, not why. They do not replace biomarkers for understanding the disease, only for ranking risk.
  3. The two gains have different baselines. The gain of 0.213 is measured against a model without cognition. The gain of 0.057 is measured against the full biomarker model. They are not additive.
  4. Associations, not causes. This is observational cohort data from a volunteer research population, not a clinical screening population.

← Mild cognitive impairment: the research library

Figures are derived from ADNI data under a Data Use Agreement. Only aggregate statistics are published; no individual participant records are shown.

The Alzheimer's Disease Neuroimaging Initiative (ADNI) is funded by the National Institute on Aging and contributions. This page is not endorsed by ADNI or the National Institute on Aging.