Ambika V. Viswanathan

Ambika V. Viswanathan

Auto-generated profile, based on publicly available information

Ambika V. Viswanathan

Department of Obstetrics and Gynecology University of North Carolina School of Medicine Chapel Hill NC USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
8 January 2024 in International Journal of Gynecology & Obstetrics
Verified
Journal Article
Open access
AVAmbika V. Viswanathan
Ambika V. Viswanathan
TPTeeranan Pokaprakarn
Teeranan Pokaprakarn
MKMargaret P. Kasaro
Margaret P. Kasaro
HSHina R. Shah
Hina R. Shah
JPJuan C. Prieto
Juan C. Prieto
JSJeffrey S. A. Stringer
Jeffrey S. A. Stringer
Objective: Low‐cost devices have made obstetric sonography possible in settings where it was previously unfeasible, but ensuring quality and consistency at scale remains a challenge. In the present study, we sought to create a tool to reduce substandard fetal biometry measurement while minimizing care disruption.Methods: We developed a deep learning artificial intelligence (AI) model to estimate gestational age (GA) in the second and third trimester from fly‐to cineloops—brief videos acquired during routine ultrasound biometry—and evaluated its performance in comparison to expert sonographer measurement. We then introduced random error into fetal biometry measurements and analyzed the ability of the AI model to flag grossly inaccurate measurements such as those that might be obtained by a novice.Results: The mean absolute error (MAE) of our model (±standard error) was 3.87 ± 0.07 days, compared to 4.80 ± 0.10 days for expert biometry (difference −0.92 days; 95% CI: −1.10 to −0.76). Based on simulated novice biometry with average absolute error of 7.5%, our model reliably detected cases where novice biometry differed from expert biometry by 10 days or more, with an area under the receiver operating characteristics curve of 0.93 (95% CI: 0.92, 0.95), sensitivity of 81.0% (95% CI: 77.9, 83.8), and specificity of 89.9% (95% CI: 88.1, 91.5). These results held across a range of sensitivity analyses, including where the model was provided suboptimal truncated fly‐to cineloops.Conclusions: Our AI model estimated GA more accurately than expert biometry. Because fly‐to cineloop videos can be obtained without any change to sonographer workflow, the model represents a no‐cost guardrail that could be incorporated into both low‐cost and commercial ultrasound devices to prevent reporting of most gross GA estimation errors.

5 June 2025 in Ultrasound in Obstetrics & Gynecology
Verified
Journal Article
Closed access
KRKatelyn Rittenhouse
Katelyn Rittenhouse
AVA. V. Viswanathan
A. V. Viswanathan
TPT. Pokaprakarn
T. Pokaprakarn
YSY. V. Sebastião
Y. V. Sebastião
ESE. Stringer
E. Stringer
JSJ. S. A. Stringer
J. S. A. Stringer

13 October 2022
Verified
Conference Paper
Closed access
AVA. Viswanathan
A. Viswanathan
MUM. Umamaheswari
M. Umamaheswari
MJM. Jaganathan
M. Jaganathan
JWJulius B. Wosowei
Julius B. Wosowei
RPRohi Prasad
Rohi Prasad
PIP. Indira
P. Indira
Agriculture is the backbone of our nation. Not only in India, but the growth of food and other crops is also an essential occupation all over the world. One of the major requirements of great yield in agriculture is the analysis of the soil and the atmosphere. This study aims in finding the best Machine Learning (ML) model that can be used to determine the right fertilizer based on all the factors like environmental conditions and crop requirements. For this purpose, three different ML models were developed using three different algorithms. The algorithms used in this study were the Neural Network (NN), Classification and Regression Tree (CART), and Linear Discriminant Analysis (LDA). Before the models were constructed, a dataset consisting of all necessary data about crops and the environment is obtained from Kaggle. This dataset then undergoes a couple of processes named encoding and upsampling to ensure the better performance of the ML models. The models are then trained using this preprocessed dataset. An unused part of the dataset is then used to test the efficiency of the models. This analysis is done using four parameters named the True Positive Rate (TPR), True Negative Rate (TNR), False Positive Rate (FPR), and False Negative Rate (FNR). By the end of this analysis, it is found that the NN algorithm is the best algorithm that can be used to predict the best fertilizer with the perfect score of 100 as a true negative rate. The LDA algorithm has the least right predictions and the maximum number of false predictions making it the worst algorithm among the three. The best algorithm, i.e., the model designed using the NN algorithm is deployed into a software application. Users can enter all the necessary details to find the most suitable fertilizer for crops based on environmental factors and crop requirements.

31 July 2022 in International journal of health sciences
Verified
Journal Article
Open access
PDF file
ARAnantha Raman Rathinam
Anantha Raman Rathinam
AVA. Viswanathan
A. Viswanathan
MUM. Umamaheswari
M. Umamaheswari
ANAnandh Nagarajan
Anandh Nagarajan
MKM.S. Rajesh Kumar
M.S. Rajesh Kumar
Cardiovascular diseases are among the foremost common serious diseases’ poignant human health. Disorder is also prevented or relieved by early diagnosis, and this might scale back mortality rates. Distinctive risk factors mistreatment machine learning models may be a promising approach. The model that comes with totally different strategies to realize effective prediction of heart disease. For this planned model to be successful, economical information collection, information Pre-processing and information Transformation methods to form correct info for the coaching model. The model has a combined dataset. Appropriate options are hand-picked by using the Relief and LASSO techniques. New hybrid classifiers like Random Forest based Machine Learning are developed by group action the normal classifiers with fabric and boosting methods, that are employed in the coaching process. Some machine learning algorithms to calculate the accuracy, sensitivity, error rate, precision. The results are shown singly to supply comparisons. Supported the result analysis will conclude that our planned model created the very best accuracy whereas mistreatment RFBM and Relief feature choice method.