scholarly journals Learning and Mapping Lyme Disease Patient Trajectories from Electronic Medical Data for Stratification of Disease Risk and Therapeutic Response

2017 ◽  
Author(s):  
Osamu Ichikawa ◽  
Benjamin S. Glicksberg ◽  
Brian Kidd ◽  
Li Li ◽  
Joel T. Dudley
Keyword(s):  
Lyme Disease ◽  
Precision Medicine ◽  
Disease Risk ◽  
Disease Patient ◽  
Tear Film ◽  
Drug Repurposing ◽  
Not Otherwise Specified ◽  
Precise Understanding ◽  
New Findings ◽  
Machine Learning Approach

ABSTRACTBackgroundLyme disease (LD) is an epidemic, tick-borne illness with approximately 329,000 incidences diagnosed each year in United States. Long-term use of antibiotics is associated with serious complications, including post-treatment Lyme disease syndrome (PTLDS). The landscape of comorbidities and health trajectories associated with LD and associated treatments is not fully understood. Consequently, there is an urgent need to improve clinical management of LD based on a more precise understanding of disease and patient stratification.MethodsWe used a precision medicine machine-learning approach based on high-dimensional electronic medical records (EMRs) to characterize the heterogeneous comorbidities in a LD population and develop systematic predictive models for identifying medications that influence the risk of subsequent comorbidities.FindingsWe identified 3, 16, and 17 comorbidities at broad disease categories associated with LD within 2, 5, and 10 years of diagnosis, respectively. At higher resolution of ICD-9 levels, we pinpointed specific co-morbid diseases on a timescale that matched the symptoms associated with PTLDS. We identified 7, 30, and 35 medications that influenced the risks of the reported comorbidities within 2, 5, and 10 years, respectively. These medications included six previously associated with the identified comorbidities and 29 new findings. For instance, the first-line antibiotic doxycycline exhibited a consistently protective effect for typical symptoms of LD, including ‘backache Not Otherwise Specified (NOS)’ and ‘chronic rhinitis’, but consistently increased the risk of ‘cataract NOS’, ‘tear film insufficiency NOS’, and ‘nocturia’.InterpretationOur approach and findings suggest new hypotheses for precision medicine treatments regimens and drug repurposing opportunities tailored to the phenotypic profiles of LD patients.FundingThe Steven & Alexandra Cohen Foundation

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

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Osamu Ichikawa ◽  
Benjamin S. Glicksberg ◽  
Nicholas Genes ◽  
Brian A. Kidd ◽  
Li Li ◽  
...  
Keyword(s):  
Lyme Disease ◽  
Therapeutic Response ◽  
Disease Risk ◽  
Disease Patient ◽  
Medical Data

scholarly journals Swarm Learning for decentralized and confidential clinical machine learning

Nature ◽  
2021 ◽  
Author(s):  
Stefanie Warnat-Herresthal ◽  
◽  
Hartmut Schultze ◽  
Krishnaprasad Lingadahalli Shastry ◽  
Sathyanarayanan Manamohan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Precision Medicine ◽  
Distributed Data ◽  
X Ray ◽  
Uniform Distributions ◽  
Privacy Laws ◽  
Data Owner ◽  
Machine Learning Approach ◽  
Chest X Ray ◽  
Privacy Legislation

AbstractFast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning—a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.

scholarly journals Impact of the experimental removal of lizards on Lyme disease risk

2011 ◽  
Vol 278 (1720) ◽  
pp. 2970-2978 ◽  
Author(s):  
Andrea Swei ◽  
Richard S. Ostfeld ◽  
Robert S. Lane ◽  
Cheryl J. Briggs
Keyword(s):  
Lyme Disease ◽  
Disease Ecology ◽  
Disease Risk ◽  
Large Fraction ◽  
Host Community ◽  
Deer Mice ◽  
Infection Prevalence ◽  
Alternate Host ◽  
Experimental Removal ◽  
Tick Infection

The distribution of vector meals in the host community is an important element of understanding and predicting vector-borne disease risk. Lizards (such as the western fence lizard; Sceloporus occidentalis ) play a unique role in Lyme disease ecology in the far-western United States. Lizards rather than mammals serve as the blood meal hosts for a large fraction of larval and nymphal western black-legged ticks ( Ixodes pacificus —the vector for Lyme disease in that region) but are not competent reservoirs for the pathogen, Borrelia burgdorferi . Prior studies have suggested that the net effect of lizards is to reduce risk of human exposure to Lyme disease, a hypothesis that we tested experimentally. Following experimental removal of lizards, we documented incomplete host switching by larval ticks (5.19%) from lizards to other hosts. Larval tick burdens increased on woodrats, a competent reservoir, but not on deer mice, a less competent pathogen reservoir. However, most larvae failed to find an alternate host. This resulted in significantly lower densities of nymphal ticks the following year. Unexpectedly, the removal of reservoir-incompetent lizards did not cause an increase in nymphal tick infection prevalence. The net result of lizard removal was a decrease in the density of infected nymphal ticks, and therefore a decreased risk to humans of Lyme disease. Our results indicate that an incompetent reservoir for a pathogen may, in fact, increase disease risk through the maintenance of higher vector density and therefore, higher density of infected vectors.

Diversifying forest communities may change Lyme disease risk: extra dimension to the dilution effect in Europe

Parasitology ◽  
2016 ◽  
Vol 143 (10) ◽  
pp. 1310-1319 ◽  
Author(s):  
SANNE C. RUYTS ◽  
EVY AMPOORTER ◽  
ELENA C. COIPAN ◽  
LANDER BAETEN ◽  
DIETER HEYLEN ◽  
...  
Keyword(s):  
North America ◽  
Lyme Disease ◽  
Borrelia Burgdorferi ◽  
Disease Risk ◽  
Severe Disease ◽  
Dilution Effect ◽  
Ixodid Ticks ◽  
Infection Prevalence ◽  
Host Diversity ◽  
Pine Stands

SUMMARYLyme disease is caused by bacteria of theBorrelia burgdorferigenospecies complex and transmitted by Ixodid ticks. In North America only one pathogenic genospecies occurs, in Europe there are several. According to the dilution effect hypothesis (DEH), formulated in North America, nymphal infection prevalence (NIP) decreases with increasing host diversity since host species differ in transmission potential. We analysedBorreliainfection in nymphs from 94 forest stands in Belgium, which are part of a diversification gradient with a supposedly related increasing host diversity: from pine stands without to oak stands with a shrub layer. We expected changing tree species and forest structure to increase host diversity and decrease NIP. In contrast with the DEH, NIP did not differ between different forest types. Genospecies diversity however, and presumably also host diversity, was higher in oak than in pine stands. Infected nymphs tended to harbourBorrelia afzeliiinfection more often in pine stands whileBorrelia gariniiandBorrelia burgdorferiss. infection appeared to be more prevalent in oak stands. This has important health consequences, since the latter two cause more severe disease manifestations. We show that the DEH must be nuanced for Europe and should consider the response of multiple pathogenic genospecies.

scholarly journals The Borrelia burgdorferi 37-Kilodalton Immunoblot Band (P37) Used in Serodiagnosis of Early Lyme Disease Is the flaA Gene Product

1999 ◽  
Vol 37 (3) ◽  
pp. 548-552 ◽  
Author(s):  
Robert D. Gilmore ◽  
Rendi L. Murphree ◽  
Angela M. James ◽  
Sarah A. Sullivan ◽  
Barbara J. B. Johnson
Keyword(s):  
Lyme Disease ◽  
Borrelia Burgdorferi ◽  
Genomic Library ◽  
Disease Patient ◽  
Humoral Response ◽  
Immunoglobulin M ◽  
Leader Peptide ◽  
Serum Samples ◽  
Present Generation ◽  
Periplasmic Flagella

The 37-kDa protein (P37) of Borrelia burgdorferi is an antigen that elicits an early immunoglobulin M (IgM) antibody response in Lyme disease patients. The P37 gene was cloned from aB. burgdorferi genomic library by screening with antibody from a Lyme disease patient who had developed a prominent humoral response to the P37 antigen. DNA sequence analysis of this clone revealed the identity of P37 to be FlaA, an outer sheath protein of the periplasmic flagella. Recombinant P37 expression was accomplished inEscherichia coli by using a gene construct with the leader peptide deleted and fused to a 38-kDa E. coli protein. The recombinant antigen was reactive in IgM immunoblots using serum samples from patients clinically diagnosed with early Lyme disease that had been scored positive for B. burgdorferi anti-P37 reactivity. Lyme disease patient samples serologically negative for theB. burgdorferi P37 protein did not react with the recombinant. Recombinant P37 may be a useful component of a set of defined antigens for the serodiagnosis of early Lyme disease. This protein can be utilized as a marker in diagnostic immunoblots, aiding in the standardization of the present generation of IgM serologic tests.

scholarly journals Drug Repurposing Prediction for Immune-Mediated Cutaneous Diseases using a Word-Embedding–Based Machine Learning Approach

2019 ◽  
Vol 139 (3) ◽  
pp. 683-691 ◽  
Author(s):  
Matthew T. Patrick ◽  
Kalpana Raja ◽  
Keylonnie Miller ◽  
Jason Sotzen ◽  
Johann E. Gudjonsson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Repurposing ◽  
Word Embedding ◽  
Learning Approach ◽  
Immune Mediated ◽  
Machine Learning Approach

scholarly journals Comparing the Climatic and Landscape Risk Factors for Lyme Disease Cases in the Upper Midwest and Northeast United States

2020 ◽  
Vol 17 (5) ◽  
pp. 1548
Author(s):  
Yuting Dong ◽  
Zheng Huang ◽  
Yong Zhang ◽  
Yingying X.G. Wang ◽  
Yang La
Keyword(s):  
United States ◽  
Risk Factors ◽  
Lyme Disease ◽  
Disease Risk ◽  
Ixodes Scapularis ◽  
Upper Midwest ◽  
Related Factors ◽  
Vector Borne Diseases ◽  
Landscape Factors ◽  
Lyme Disease Risk

Lyme disease, recognized as one of the most important vector-borne diseases worldwide, has been increasing in incidence and spatial extend in United States. In the Northeast and Upper Midwest, Lyme disease is transmitted by Ixodes scapularis. Currently, many studies have been conducted to identify factors influencing Lyme disease risk in the Northeast, however, relatively few studies focused on the Upper Midwest. In this study, we explored and compared the climatic and landscape factors that shape the spatial patterns of human Lyme cases in these two regions, using the generalized linear mixed models. Our results showed that climatic variables generally had opposite correlations with Lyme disease risk, while landscape factors usually had similar effects in these two regions. High precipitation and low temperature were correlated with high Lyme disease risk in the Upper Midwest, while with low Lyme disease risk in the Northeast. In both regions, size and fragmentation related factors of residential area showed positive correlations with Lyme disease risk. Deciduous forests and evergreen forests had opposite effects on Lyme disease risk, but the effects were consistent between two regions. In general, this study provides new insight into understanding the differences of risk factors of human Lyme disease risk in these two regions.

Sign in / Sign up

Export Citation Format

Share Document