Genetic Testing in patients with Dementia: A Data-Driven Clinical Decision Tree for Memory Clinics
van der Lee, S. J.; Hulsman, M.; van Spaendonk, R. M. L.; van der Schaar, J. J.; Dijkstra, J. I. R.; Tesi, N.; van der Flier, W. M.; van Ruissen, F.; Elting, M.; Reinders, M. J. T.; de Rojas, I.; van Haelst, M. M.; Verschuuren-Bemelmans, C. C.; de Geus, C. M.; Pijnenburg, Y. A. L.; Holstege, H.
Show abstract
ImportanceIdentifying genetic causes for dementia in patients who visit a memory clinic is important for patients and family members. However, current clinical selection criteria for genetic analysis may miss carriers of pathogenic genetic variants (PGVs) in dementia-related genes. ObjectiveOptimizing the patient-selection criteria for offering genetic counselling in patients visiting memory clinics. DesignClinical cohort study at the Alzheimer Center Amsterdam, analysing patients from January 2010 to June 2012, and who participated in the Amsterdam Dementia Cohort. A 54-gene dementia panel was used to identify PGVs, class IV/V variants according to the American College of Medical Genetics and Genomics (ACMG) guidelines. Subsequently, we formulated a novel decision tree to determine eligibility for genetic testing, allowing optimal identification of symptomatic PGV carriers. The decision tree was prospectively applied in the same memory clinic for one year (2021-2022). SettingThe Alzheimer Center Amsterdam, a specialized memory clinic in the Netherlands. ParticipantsA total of 1,138 patients visited the memory clinic (2010-2012), of whom 1,022 were genetically analysed [90%]. Of the analysed patients 413 were female [40.4%], mean [SD] age at presentation 62.1 [8.9] years. The decision tree was applied to 517 patients that visited the memory clinic between 2021-2022; 215[41.6%] female, mean [SD] age at presentation 64.1[8.5] years. Exposurenone Main Outcome(s)Presence of a PGVs and eligibility of carriers for genetic testing based on previous and new clinical selection criteria. ResultsWe identified 34 PGV carriers, corresponding to 3.3% of all patients. Of these, 24 carriers had symptoms of dementia [n=24]. Based on previous clinical criteria, only 15 of all PGV carriers were eligible. Which was 44% of all PGV carriers [15/34] and 65% of symptomatic PGV carriers [15/24]. With the new decision tree, 22 of all PGVs were eligible 62.5% [22/34] and 91% [22/24] of all symptomatic PGV carriers were eligible. In the prospective application, 517 patients were evaluated of which 148[31%] patients were eligible for a genetic test, 103 [20%] were finally tested and 13 patients carried a PGV [2.5% of total]. There were 73% more patients with a PGV identified than anticipated. Conclusions and RelevanceOur decision tree improved the identification of patients with genetic dementias. Key PointsO_ST_ABSQuestionC_ST_ABSDo current clinical criteria for selecting dementia patients identify those with pathogenic genetic variants (PGVs) in dementia-related genes? FindingsIn a cohort study at the Alzheimer Center Amsterdam, 34 PGV carriers were identified among 1,022 patients. Previous criteria identified only 44% (15/34) of all carriers and 65% (15/24) of symptomatic carriers. A new decision tree increased this to 62.5% (22/34) and 91% (22/24), respectively. Real-life implementation improved carrier identification by 73%. MeaningOur decision tree enhances genetic dementia patient identification, offering an improved approach to identify families with familial dementia.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The Association of Alzheimer’s Disease-related Blood-based Biomarkers with Cognitive Screening Test Performance in the Congolese Population in Kinshasa 94%
- Alzheimer's disease susceptibility gene apolipoprotein e (APOE) and blood biomarkers in UK Biobank (N=395,769). 93%
- Impact of different diagnostic measures on drug class association with dementia progression risk: a longitudinal prospective cohort study 93%
Similar papers in this journal
- Brain Amyloid and the Transition to Dementia in Down Syndrome 93%
- Delayed primacy recall performance predicts post mortem Alzheimers disease pathology from unimpaired ante mortem cognitive baseline 92%
- Evaluation of a speech-based AI system for early detection of Alzheimer’s disease remotely via smartphones 92%
Similar papers in this journal
- A metabolite-based machine learning approach to diagnose Alzheimer's-type dementia in blood: Results from the European Medical Information Framework for Alzheimer's Disease biomarker discovery cohort 93%
- LD-informed deep learning for Alzheimer’s gene loci detection using WGS data 91%
- The Cognitive-Functional Composite is sensitive to clinical progression in early dementia: longitudinal findings from the Catch-Cog study cohort 91%
Similar papers in this journal
- Affective Neuropsychiatric Symptom Metrics in the National Alzheimers Coordinating Center Dataset 94%
- Frequency of Variants in Mendelian Alzheimer’s Disease Genes within the Alzheimer’s Disease Sequencing Project (ADSP) 93%
- Blood Biomarkers for Diagnosis & Differential Diagnosis of Alzheimers Disease in Real-World Clinical Populations: A Systematic Review 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.