Home › Research › Digital health tools
Detection of probable dementia cases in undiagnosed patients using structured and unstructured electronic health records
Shao Y, Zeng QT, Chen KK, Shutes-David A, Thielke SM, Tsuang DW.. BMC medical informatics and decision making, 2019-07-09
Topic: Risk, prevention and care in population studies
Background Dementia is underdiagnosed in both the general population and among Veterans. This underdiagnosis decreases quality of life, reduces opportunities for interventions, and increases health-care costs. New approaches are therefore necessary to facilitate the timely detection of dementia. This study seeks to identify cases of undiagnosed dementia by developing and validating a weakly supervised machine-learning approach that incorporates the analysis of both structured and unstructured electronic health record (EHR) data. Methods A topic modeling approach that included latent Dirichlet allocation, stable topic extraction, and random sampling was applied to VHA EHRs. Topic features from unstructured data and features from structured data were compared between Veterans with (n = 1861) and without (n = 9305) ICD-9 dementia codes. A logistic regression model was used to develop dementia prediction scores, and manual reviews were conducted to validate the machine-learning results. Results A total of 853 features were identified (290 topics, 174 non-dementia ICD codes, 159 CPT codes, 59 medications, and 171 note types) for the development of logistic regression prediction scores. These scores were validated in a subset of Veterans without ICD-9 dementia codes (n = 120) by experts in dementia who performed manual record reviews and achieved a high level of inter-rater agreement. The manual reviews were used to develop a receiver of characteristic (ROC) curve with different thresholds for case detection, including a threshold of 0.061, which produced an optimal sensitivity (0.825) and specificity (0.832). Conclusions Dementia is underdiagnosed, and thus, ICD codes alone cannot serve as a gold standard for diagnosis. However, this study suggests that imperfect data (e.g., ICD codes in combination with other EHR features) can serve as a silver standard to develop a risk model, apply that model to patients without dementia codes, and then select a case-detection threshold. The study is one of the first to utilize both structured and unstructured EHRs to develop risk scores for the diagnosis of dementia.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Shao, Y., Zeng, Q. T., Chen, K. K., Shutes-David, A., Thielke, S. M., & Tsuang, D. W. (2019). Detection of probable dementia cases in undiagnosed patients using structured and unstructured electronic health records. BMC medical informatics and decision making. https://doi.org/10.1186/s12911-019-0846-4
Vancouver
Shao Y, Zeng QT, Chen KK, Shutes-David A, Thielke SM, Tsuang DW. Detection of probable dementia cases in undiagnosed patients using structured and unstructured electronic health records. BMC medical informatics and decision making. 2019. doi:10.1186/s12911-019-0846-4. PMID: 31288818.
BibTeX
@article{shao2019-31288818,
author = {Shao, Y. and Zeng, Q. T. and Chen, K. K. and Shutes-David, A. and Thielke, S. M. and Tsuang, D. W.},
title = {{Detection of probable dementia cases in undiagnosed patients using structured and unstructured electronic health records}},
journal = {BMC medical informatics and decision making},
year = {2019},
doi = {10.1186/s12911-019-0846-4},
pmid = {31288818},
url = {https://doi.org/10.1186/s12911-019-0846-4}
}
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.
Key findings
- A logistic regression model was used to develop dementia prediction scores, and manual reviews were conducted to validate the machine-learning results.
- Results A total of 853 features were identified (290 topics, 174 non-dementia ICD codes, 159 CPT codes, 59 medications, and 171 note types) for the development of logistic regression prediction scores.
- However, this study suggests that imperfect data (e.g., ICD codes in combination with other EHR features) can serve as a silver standard to develop a risk model, apply that model to patients without dementia codes, and then select a case-detection threshold.
Why it matters
This study developed a weakly supervised machine learning approach using structured and unstructured electronic health record data to detect probable dementia cases in undiagnosed patients. It is about detection and does not test any treatment, cure or prevention.
New to this subject? Start with our plain-English guide: Digital health →
Study details
- Participants1,861
- Evidence strengthLow
How this study scored 53/100
Published in a peer-reviewed journal. Scored zero for study design, effect reported and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (BMC medical informatics and decision making) |
| Journal's citation record | 1 / 4 | BMC Medical Informatics and Decision Making: journal h-index 145 (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 | 1 / 5 | Rated “low” 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 | 3 / 4 | 1,861 participants |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 4 / 7 | Cited 84 times (OpenAlex, 2026-10-10) |
| Citations per year | 3 / 5 | 9.3 citations a year over 9 year(s) since 2019 |
| Impact for its field and year | 3 / 6 | Cited 3.8× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 2 / 6 | Cited by 3 other studies in this library |
| Still being cited | 2 / 4 | Cited 30 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 3 / 4 | Last-listed author Debby W. Tsuang: h-index 70 (OpenAlex, whole career) |
| Institution's track record | 3 / 3 | University of Washington: institution h-index 3,540 (OpenAlex) |
| Multi-centre collaboration | 2 / 3 | OpenAlex lists 5 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 31288818) |
| Free to read | 2 / 2 | Free to read |
| Total | 53 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.1186/s12911-019-0846-4
- PubMed: 31288818
- Original source →
- Free full text: BMC Medical Informatics and Decision Making →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Related
Studies in the library that share something with this one. The line above each title says what.
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Later studies that cite this one
3 studies in the alzhub library list this one in their references.
Related studies in Digital health tools
Also tagged “prevalence”
1,223 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 1,223 tagged studies.