Home › Research › Digital health tools
Identifying incident dementia by applying machine learning to a very large administrative claims dataset
Nori VS, Hane CA, Martin DC, Kravetz AD, Sanghavi DM.. PloS one, 2019-07-05
Topic: Risk, prevention and care in population studies
Alzheimer's disease and related dementias (ADRD) are highly prevalent conditions, and prior efforts to develop predictive models have relied on demographic and clinical risk factors using traditional logistical regression methods. We hypothesized that machine-learning algorithms using administrative claims data may represent a novel approach to predicting ADRD. Using a national de-identified dataset of more than 125 million patients including over 10,000 clinical, pharmaceutical, and demographic variables, we developed a cohort to train a machine learning model to predict ADRD 4-5 years in advance. The Lasso algorithm selected a 50-variable model with an area under the curve (AUC) of 0.693. Top diagnosis codes in the model were memory loss (780.93), Parkinson's disease (332.0), mild cognitive impairment (331.83) and bipolar disorder (296.80), and top pharmacy codes were psychoactive drugs. Machine learning algorithms can rapidly develop predictive models for ADRD with massive datasets, without requiring hypothesis-driven feature engineering.
Key findings
- We hypothesized that machine-learning algorithms using administrative claims data may represent a novel approach to predicting ADRD.
- Using a national de-identified dataset of more than 125 million patients including over 10,000 clinical, pharmaceutical, and demographic variables, we developed a cohort to train a machine learning model to predict ADRD 4-5 years in advance.
- The Lasso algorithm selected a 50-variable model with an area under the curve (AUC) of 0.693.
- Top diagnosis codes in the model were memory loss (780.93), Parkinson's disease (332.0), mild cognitive impairment (331.83) and bipolar disorder (296.80), and top pharmacy codes were psychoactive drugs.
- Machine learning algorithms can rapidly develop predictive models for ADRD with massive datasets, without requiring hypothesis-driven feature engineering.
Why it matters
A machine learning model using administrative claims data predicted Alzheimer's disease and related dementias 4-5 years in advance with an area under the curve of 0.693. This is a prediction tool only and does not treat, cure or prevent dementia.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Evidence strengthModerate
How this study scored 46/100
Published in a peer-reviewed journal. Scored zero for study design, sample size, effect reported, studied in people and randomised / blinded because the record does not state it. We have no data on institution's track record, so that was left out: it earned 45 of the 97 points we could judge it on, which is 46 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (PloS one) |
| Journal's citation record | 4 / 4 | PLoS ONE: journal h-index 594 (OpenAlex, 2026-10-29) |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 3 / 5 | Rated “moderate” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 2 / 5 | 2019 — within 10 year(s) of the newest study here |
| Sample size | 0 / 4 | Participant count not stated — scores zero (not stated in the record — scored 0) |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 0 / 3 | Not stated whether this was studied in people — scores zero (not stated in the record — scored 0) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 4 / 7 | Cited 60 times (OpenAlex, 2026-10-10) |
| Citations per year | 2 / 5 | 6.7 citations a year over 9 year(s) since 2019 |
| Impact for its field and year | 3 / 6 | Cited 4.6× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 2 / 6 | Cited by 6 other studies in this library |
| Still being cited | 2 / 4 | Cited 26 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Darshak M. Sanghavi: h-index 22 (OpenAlex, whole career) |
| Institution's track record | — / 3 | No institution listed in OpenAlex — left out of this score |
| Multi-centre collaboration | 0 / 3 | OpenAlex lists 0 institution(s) in 0 countries — scores zero (affiliation lists can be incomplete) |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 31276468) |
| Free to read | 2 / 2 | Free to read |
| Points | 45 / 97 | Scored on 19 of 20 parts. We have no data for the rest, so they are left out: 45 of the 97 points we could judge it on is 46 out of 100. |
| Total | 46 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.
APA 7th
Nori, V. S., Hane, C. A., Martin, D. C., Kravetz, A. D., & Sanghavi, D. M. (2019). Identifying incident dementia by applying machine learning to a very large administrative claims dataset. PloS one. https://doi.org/10.1371/journal.pone.0203246
Vancouver
Nori VS, Hane CA, Martin DC, Kravetz AD, Sanghavi DM. Identifying incident dementia by applying machine learning to a very large administrative claims dataset. PloS one. 2019. doi:10.1371/journal.pone.0203246. PMID: 31276468.
BibTeX
@article{nori2019-31276468,
author = {Nori, V. S. and Hane, C. A. and Martin, D. C. and Kravetz, A. D. and Sanghavi, D. M.},
title = {{Identifying incident dementia by applying machine learning to a very large administrative claims dataset}},
journal = {PloS one},
year = {2019},
doi = {10.1371/journal.pone.0203246},
pmid = {31276468},
url = {https://doi.org/10.1371/journal.pone.0203246}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here. Showing 12 of 14.
Later studies that cite this one
6 studies in the alzhub library list this one in their references.
Related studies in Digital health tools
Also tagged “prevalence”
1,224 studies in the library carry the topic tag “prevalence”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,224 tagged studies.