Table 1 The number of variables selected by information retrieval models for each risk factor category
Target phrasea | Number of selected phrases | Similarity score from word2vec mean (range) | Similarity score from doc2vec mean (range) |
|---|---|---|---|
Alcohol | 17 | 0.78 (0.66, 1.0) | 0.49 (0.41, 0.58) |
Anxiety | 14 | 0.7 (0.62, 0.85) | 0.55 (0.44, 0.61) |
Arthritis | 5 | 0.68 (0.58, 0.76) | 0.56 (0.53, 0.59) |
Atrial Fibrillation | 6 | 0.64 (0.54, 0.8) | 0.57 (0.53, 0.6) |
Cancer | 10 | 0.76 (0.65, 0.81) | 0.54 (0.46, 0.61) |
Carotid atherosclerosis | 4 | 0.72 (0.71, 0.74) | 0.51 (0.49, 0.54) |
Cholesterol | 72 | 0.72 (0.1, 1.0) | 0.58 (0.52, 0.66) |
Cognitive decline | 9 | 0.66 (0.6, 0.73) | 0.58 (0.46, 0.64) |
Cognitive engagement | 2 | 0.69 (0.66, 0.73) | 0.59 (0.57, 0.62) |
Dementia | 2 | 0.63 (0.62, 0.64) | 0.59 (0.59, 0.59) |
Depression | 10 | 0.7 (0.58, 0.76) | 0.5 (0.44, 0.6) |
Diabetes | 13 | 0.7 (0.61, 0.78) | 0.59 (0.58, 0.61) |
Diet | 11 | 0.77 (0.71, 0.87) | 0.5 (0.42, 0.58) |
Hearing loss | 5 | 0.81 (0.78, 0.84) | 0.46 (0.41, 0.5) |
Hypertension | 4 | 0.79 (0.77, 0.82) | 0.61 (0.6, 0.61) |
Inflammatory markers | 1 | 0.61 (0.61, 0.61) | 0.59 (0.59, 0.59) |
Memory loss | 1 | 0.75 (0.75, 0.75) | 0.57 (0.57, 0.57) |
Metabolic syndrome | 15 | 0.65 (0.62, 0.71) | 0.61 (0.59, 0.64) |
Motor function | 8 | 0.64 (0.59, 0.74) | 0.6 (0.58, 0.61) |
Noneb | 58 | 0.64 (0.52, 0.76) | 0.59 (0.43, 0.66) |
Peripheral artery disease | 8 | 0.66 (0.59, 0.74) | 0.6 (0.58, 0.63) |
Pesticides | 1 | 0.77 (0.77, 0.77) | 0.47 (0.47, 0.47) |
Physical activity | 12 | 0.77 (0.7, 0.82) | 0.46 (0.4, 0.5) |
Renal disease | 14 | 0.71 (0.65, 0.77) | 0.56 (0.54, 0.6) |
Sleep | 5 | 0.76 (0.67, 0.85) | 0.54 (0.49, 0.6) |
Smoking | 19 | 0.78 (0.61, 0.9) | 0.46 (0.41, 0.62) |
Social engagement | 2 | 0.64 (0.63, 0.64) | 0.6 (0.6, 0.61) |
Stress | 4 | 0.62 (0.49, 0.69) | 0.59 (0.58, 0.6) |
Stroke | 12 | 0.67 (0.59, 0.74) | 0.6 (0.56, 0.65) |
