Lyme Disease Patient Trajectories Learned from Electronic Medical Data for Stratification of Disease Risk and Therapeutic Response

Abstract

Lyme disease (LD) is the most common tick-borne illness in the United States. Although appropriate antibiotic treatment is effective for most cases, up to 20% of patients develop post-treatment Lyme disease syndrome (PTLDS). There is an urgent need to improve clinical management of LD using precise understanding of disease and patient stratification. We applied machine-learning to electronic medical records to better characterize the heterogeneity of LD and developed predictive models for identifying medications that are associated with risks of subsequent comorbidities. For broad disease categories, we identified 3, 16, and 17 comorbidities within 2, 5, and 10 years of diagnosis, respectively. At a higher resolution of ICD-9 codes, we identified known associations with LD including chronic pain and cognitive disorders, as well as particular comorbidities on a timescale that matched PTLDS symptomology. We identified 7, 30, and 35 medications associated with risks of these comorbidities within 2, 5, and 10 years, respectively. For instance, the first-line antibiotic doxycycline exhibited a consistently protective association for typical symptoms of LD, including backache. Our approach and findings may suggest new hypotheses for more personalized treatments regimens for LD patients.

Figure 1

Workflow of the study, outlining steps from data organization to statistical methodologies.

Figure 2

Medication–Lyme disease comorbidity network, analyzed by CCS-single-level categories, in time windows of 5 years (A) and 10 years (B). Significant associations between medications (cyan) and comorbidities (magenta) are connected by red or blue lines (p < 0.1). Red lines indicate risk associations (OR > 1), and blue lines indicate protective associations (OR < 1). Medications and indications (green) were connected based on information in the public knowledgebase MEDI.

Figure 3

Medication–Lyme disease comorbidity network at the ICD-9 levels in time windows of 5 years (A) and 10 years (B). Significant associations between medications (cyan) and comorbidities (magenta) are connected by red or blue lines (p < 0.1). Red lines indicate risk associations (OR > 1), and blue lines indicate protective associations (OR < 1).

Figure 4

Kaplan–Meier plot of propensity-score-matched survival analysis (a) doxycycline–‘backache NOS’ (ICD-9 code: 724.5), (b) doxycycline–‘chronic rhinitis’ (472.0), and (c) amoxicillin–‘acute URI NOS’ (465.9).