alzhub.org
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.

Home › Research › Topics › Mild cognitive impairment › ADNI conversion

From MCI to Alzheimer's: what 2,430 participants show

30.2% of the 988 followed participants with MCI had converted to dementia by 36 months, and CSF markers separated them best (AUC 0.739 for CSF Aβ42).

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.

Who was in the cohort

Baseline diagnosis of 2,430 participants: CN 542, MCI 1,113, Dementia 411, SMC 353, missing 11
  • Cognitively normal: 542
  • Mild cognitive impairment: 1,113
  • Dementia: 411
  • Significant memory concern: 353
  • Diagnosis missing: 11

Baseline diagnosis of all 2,430 ADNI participants. The MCI group (1,113) is the one followed for conversion.

How fast MCI converts

Cumulative conversion from MCI to dementia: 8.2% at 12 months (95% CI 6.6 to 10.1); 20.9% at 24 months (95% CI 18.4 to 23.7); 30.2% at 36 months (95% CI 27.2 to 33.4); 37.7% at 48 months (95% CI 34.3 to 41.3) 0% 10% 20% 30% 40% 50% 0 12 24 36 48 8.2% 20.9% 30.2% 37.7% Months from baseline Cumulative conversion

Kaplan-Meier cumulative conversion to dementia; the line is the estimate, the shaded band and whiskers the 95% CI. n = 988 MCI participants analysed.

Of 1,113 MCI at baseline, 114 were excluded for no follow-up, leaving 988.

Which baseline markers predict it

AUC for predicting conversion by 36 months, highest first: CSF Aβ42 0.739; CSF p-tau181 0.732; CSF total tau 0.723; Hippocampal volume / ICV 0.685; APOE4 carrier vs non-carrier 0.643; Age at baseline 0.556 0.5 0.6 0.7 0.8 0.9 1.0 0.5 = chance CSF Aβ42 0.739 n = 484 · per 1 SD; lower = higher risk · 95% CI 0.694–0.784 CSF p-tau181 0.732 n = 484 · per 1 SD; higher = higher risk · 95% CI 0.685–0.779 CSF total tau 0.723 n = 484 · per 1 SD; higher = higher risk · 95% CI 0.676–0.771 Hippocampal volume / ICV 0.685 n = 266 · 95% CI 0.621–0.748 APOE4 carrier vs non-carrier 0.643 n = 719 · 95% CI 0.607–0.680 Age at baseline 0.556 n = 728 · per year · 95% CI 0.513–0.599

AUC for conversion by 36 months, one marker at a time; the bar is the estimate, the whiskers the 95% CI. n varies by marker (266–728).

What this means

  1. CSF Aβ42 — 0.739
  2. CSF p-tau181 — 0.732
  3. CSF total tau — 0.723
  4. Hippocampal volume / ICV — 0.685
  5. APOE4 carrier vs non-carrier — 0.643
  6. Age at baseline — 0.556

CSF markers lead, hippocampal volume is close behind, APOE4 is weaker, and age is weakest. A joint Cox model reached a C-index of 0.676 in-sample and 0.637 under 5-fold cross-validation, with a time-dependent AUC of 0.748 at 36 months. On their own, CSF tau and p-tau each carry a hazard ratio of about 1.6 per SD; in the joint model their estimates become unstable because the two are highly correlated.

Read these caveats first

  1. In-sample versus cross-validated. The C-index of 0.676 is measured on the same data the model was fitted to; under 5-fold cross-validation it drops to 0.637.
  2. Visit windows. A conversion recorded at the “month 36” visit is often dated slightly after 36 months, so it misses a strict cutoff. With a 3-month visit window the 36-month rate is 34.4% rather than 30.2%, and the 12-month rate is 12.8% rather than 8.2%.
  3. Assay ceiling. 192 baseline Abeta values were at the assay ceiling (reported as “>1700”) and are treated as equal to that ceiling.
  4. Associations, not causes. This is observational cohort data, and the cohort is a volunteer research population, not a clinical screening population.

← Mild cognitive impairment: the research library · All research topics

Related ADNI analyses: the multimodal model · what baseline cognition adds · how the measures correlate

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.