Ravikiran Keshavamurthy

Dr. Ravikiran Keshavamurthy

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 January 2022 in Pathogens
Verified
Journal Article
Open access
PDF file
SDSamuel Dixon
Samuel Dixon
RKRavikiran Keshavamurthy
Ravikiran Keshavamurthy
DFDaniel H. Farber
Daniel H. Farber
ASAndrew Stevens
Andrew Stevens
KPKarl T. Pazdernik
Karl T. Pazdernik
Lauren CharlesLauren Charles
Lauren Charles
Accurate infectious disease forecasting can inform efforts to prevent outbreaks and mitigate adverse impacts. This study compares the performance of statistical, machine learning (ML), and deep learning (DL) approaches in forecasting infectious disease incidences across different countries and time intervals. We forecasted three diverse diseases: campylobacteriosis, typhoid, and Q-fever, using a wide variety of features (n = 46) from public datasets, e.g., landscape, climate, and socioeconomic factors. We compared autoregressive statistical models to two tree-based ML models (extreme gradient boosted trees [XGB] and random forest [RF]) and two DL models (multi-layer perceptron and encoder–decoder model). The disease models were trained on data from seven different countries at the region-level between 2009–2017. Forecasting performance of all models was assessed using mean absolute error, root mean square error, and Poisson deviance across Australia, Israel, and the United States for the months of January through August of 2018. The overall model results were compared across diseases as well as various data splits, including country, regions with highest and lowest cases, and the forecasted months out (i.e., nowcasting, short-term, and long-term forecasting). Overall, the XGB models performed the best for all diseases and, in general, tree-based ML models performed the best when looking at data splits. There were a few instances where the statistical or DL models had minutely smaller error metrics for specific subsets of typhoid, which is a disease with very low case counts. Feature importance per disease was measured by using four tree-based ML models (i.e., XGB and RF with and without region name as a feature). The most important feature groups included previous case counts, region name, population counts and density, mortality causes of neonatal to under 5 years of age, sanitation factors, and elevation. This study demonstrates the power of ML approaches to incorporate a wide range of factors to forecast various diseases, regardless of location, more accurately than traditional statistical approaches.

1 May 2019 in Preventive Veterinary Medicine
Verified
Journal Article
Closed access
RKRavikiran Keshavamurthy
Ravikiran Keshavamurthy
BSBalbir Bagicha Singh
Balbir Bagicha Singh
DKD.G. Kalambhe
D.G. Kalambhe
RAR.S. Aulakh
R.S. Aulakh
Navneet DhandNavneet Dhand
Navneet Dhand

22 June 2021 in Pathogens
Verified
Journal Article
Open access
PDF file
RKRavikiran Keshavamurthy
Ravikiran Keshavamurthy
STS. M. Thumbi
S. M. Thumbi
Lauren CharlesLauren Charles
Lauren Charles
Infectious disease surveillance is crucial for early detection and situational awareness of disease outbreaks. Digital biosurveillance monitors large volumes of open-source data to flag potential health threats. This study investigates the potential of digital surveillance in the detection of the top five priority zoonotic diseases in Kenya: Rift Valley fever (RVF), anthrax, rabies, brucellosis, and trypanosomiasis. Open-source disease events reported between August 2016 and October 2020 were collected and key event-specific information was extracted using a newly developed disease event taxonomy. A total of 424 disease reports encompassing 55 unique events belonging to anthrax (43.6%), RVF (34.6%), and rabies (21.8%) were identified. Most events were first reported by news media (78.2%) followed by international health organizations (16.4%). News media reported the events 4.1 (±4.7) days faster than the official reports. There was a positive association between official reporting and RVF events (odds ratio (OR) 195.5, 95% confidence interval (CI); 24.01–4756.43, p < 0.001) and a negative association between official reporting and local media coverage of events (OR 0.03, 95% CI; 0.00–0.17, p = 0.030). This study highlights the usefulness of local news in the detection of potentially neglected zoonotic disease events and the importance of digital biosurveillance in resource-limited settings.

21 March 2025 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
RKRavikiran Keshavamurthy
Ravikiran Keshavamurthy
KPKarl T Pazdernik
Karl T Pazdernik
CHColby Ham
Colby Ham
SDSamuel Dixon
Samuel Dixon
Samantha ErwinSamantha Erwin
Samantha Erwin
Lauren CharlesLauren Charles
Lauren Charles
Background: Infectious diseases (IDs) have a significant detrimental impact on global health. Timely and accurate ID forecasting can result in more informed implementation of control measures and prevention policies. Objective: To meet the operational decision-making needs of real-world circumstances, we aimed to build a standardized, reliable, and trustworthy ID forecasting pipeline and visualization dashboard that is generalizable across a wide range of modeling techniques, IDs, and global locations. Methods: We forecasted 6 diverse, zoonotic diseases (brucellosis, campylobacteriosis, Middle East respiratory syndrome, Q fever, tick-borne encephalitis, and tularemia) across 4 continents and 8 countries. We included a wide range of statistical, machine learning, and deep learning models (n=9) and trained them on a multitude of features (average n=2326) within the One Health landscape, including demography, landscape, climate, and socioeconomic factors. The pipeline and dashboard were created in consideration of crucial operational metrics—prediction accuracy, computational efficiency, spatiotemporal generalizability, uncertainty quantification, and interpretability—which are essential to strategic data-driven decisions. Results: While no single best model was suitable for all disease, region, and country combinations, our ensemble technique selects the best-performing model for each given scenario to achieve the closest prediction. For new or emerging diseases in a region, the ensemble model can predict how the disease may behave in the new region using a pretrained model from a similar region with a history of that disease. The data visualization dashboard provides a clean interface of important analytical metrics, such as ID temporal patterns, forecasts, prediction uncertainties, and model feature importance across all geographic locations and disease combinations. Conclusions: As the need for real-time, operational ID forecasting capabilities increases, this standardized and automated platform for data collection, analysis, and reporting is a major step forward in enabling evidence-based public health decisions and policies for the prevention and mitigation of future ID outbreaks.

5 May 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
EMEleftherios Meletis
Eleftherios Meletis
RKRavikiran Keshavamurthy
Ravikiran Keshavamurthy
BDBalbir Bagicha Singh Dhaliwal
Balbir Bagicha Singh Dhaliwal
RARabinder Singh Aulakh
Rabinder Singh Aulakh
Navneet DhandNavneet Dhand
Navneet Dhand
PKPolychronis Kostoulas
Polychronis Kostoulas
Q Fever is a zoonotic disease of significant animal and public health concern, caused by Coxiella burnetii (C. burnetii), an obligate intracellular bacterium. This study was done to evaluate the diagnostic sensitivity (DSe) and diagnostic specificity (DSp) of three diagnostic methods to diagnose C. burnetii infection in cattle and buffaloes in Punjab, India: an indirect ELISA method applied in serum samples and a trans-Polymerase Chain Reaction (transPCR) technique applied in milk samples and genital swabs, using a Bayesian latent class analysis. Conditional independence was assumed between the tests, given (i) the different biological principle of ELISA and trans-PCR and (ii) the fact that the trans-PCR was performed on different tissues. The ELISA method in the serum samples showed the highest DSe of 0.97 (95% Probability Intervals (Pis): 0.93; 0.99) compared to the trans-PCR method applied in milk samples 0.76 (0.63; 0.87) and genital swabs 0.73 (0.58; 0.85). The DSps of all tests were high, with trans-PCR in genital swabs recording the highest DSp of 0.99 (0.98; 1), while the DSp of trans-PCR in milk samples and ELISA in serum samples were 0.97 (0.95; 0.99) and 0.95 (0.93; 0.97) respectively. The study results show that none of the applied tests are perfect, therefore, a testing regimen based on the diagnostic characteristic of the tests may be considered for diagnosis of C. burnetii.

27 April 2024 in JMIR Preprints
Verified
Preprint
Open access
RKRavikiran Keshavamurthy
Ravikiran Keshavamurthy
KPKarl T Pazdernik
Karl T Pazdernik
CHColby Ham
Colby Ham
SDSamuel Dixon
Samuel Dixon
Samantha ErwinSamantha Erwin
Samantha Erwin
Lauren CharlesLauren Charles
Lauren Charles
BACKGROUND Infectious diseases (ID) have a significant detrimental impact on global health. Timely and accurate infectious disease forecasting can result in more informed implementation of control measures and prevention policies. OBJECTIVE To meet the operational decision-making needs of real-world circumstances, we aimed to build a standardized, reliable, and trustworthy ID forecasting pipeline and visualization dashboard that is generalizable across a wide range of modeling techniques, IDs, and global locations. METHODS We forecasted six diverse, zoonotic diseases (brucellosis, campylobacteriosis, Middle East respiratory syndrome, Q-fever, Tick-borne Encephalitis, and Tularemia) across 4 continents and 8 countries. We included a wide range of statistical, machine learning, and deep learning models (n=9) and trained them on a multitude of features (average n = 2326) within the One Health landscape, including demography, landscape, climate, and socioeconomic factors. The pipeline and dashboard were created in consideration of crucial operational metrics - prediction accuracy, computational efficiency, spatio-temporal generalizability, uncertainty quantification, and interpretability - which are essential to strategic data-driven decisions. RESULTS While no single best model was suitable for all disease, region, and country combinations, our ensemble technique selects the best performing model for each given scenario to achieve the closest prediction. For new or emerging diseases in a region, the ensemble model can predict how the disease may behave in the new region using a pre-trained model from a similar region with a history of that disease. The data visualization dashboard provides an interactive, clean interface of important analytical metrics, such as ID temporal patterns, forecasts, prediction uncertainties, and model feature importance across all geographic locations and disease combinations. CONCLUSIONS As the need for real-time, operational ID forecasting capabilities increases, this standardized and automated platform for data collection, analysis, and reporting is a major step forward in enabling evidence-based public health decisions and policies for prevention and mitigation of future ID outbreaks.