Kelvin Memeh

Kelvin Memeh

Auto-generated profile, based on publicly available information

Kelvin Memeh

Division of Surgical Oncology, Department of Surgery, Ohio State University Comprehensive Cancer Center and Ohio State University Wexner Medical Center , Columbus, OH 43210

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

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

Representative Publications

View All Publications
26 May 2022 in Journal of Medical Imaging
Verified
Journal Article
Closed access
PDF file
XKXavier M. Keutgen
Xavier M. Keutgen
HLHui Li
Hui Li
KMKelvin Memeh
Kelvin Memeh
JBJulian Conn Busch
Julian Conn Busch
JWJelani Williams
Jelani Williams
MGMaryellen L Giger
Maryellen L Giger
Background: Ultrasound (US)-guided fine needle aspiration (FNA) cytology is the gold standard for the evaluation of thyroid nodules. However, up to 30% of FNA results are indeterminate, requiring further testing. In this study, we present a machine-learning analysis of indeterminate thyroid nodules on ultrasound with the aim to improve cancer diagnosis. Methods: Ultrasound images were collected from two institutions and labeled according to their FNA (F) and surgical pathology (S) diagnoses [malignant (M), benign (B), and indeterminate (I)]. Subgroup breakdown (FS) included: 90 BB, 83 IB, 70 MM, and 59 IM thyroid nodules. Margins of thyroid nodules were manually annotated, and computerized radiomic texture analysis was conducted within tumor contours. Initial investigation was conducted using five-fold cross-validation paradigm with a two-class Bayesian artificial neural networks classifier, including stepwise feature selection. Testing was conducted on an independent set and compared with a commercial molecular testing platform. Performance was evaluated using receiver operating characteristic analysis in the task of distinguishing between malignant and benign nodules. Results: About 1052 ultrasound images from 302 thyroid nodules were used for radiomic feature extraction and analysis. On the training/validation set comprising 263 nodules, five-fold cross-validation yielded area under curves (AUCs) of 0.75 [Standard Error (SE) = 0.04; P < 0.001] and 0.67 (SE = 0.05; P = 0.0012) for the classification tasks of MM versus BB, and IM versus IB, respectively. On an independent test set of 19 IM/IB cases, the algorithm for distinguishing indeterminate nodules yielded an AUC value of 0.88 (SE = 0.09; P < 0.001), which was higher than the AUC of a commercially available molecular testing platform (AUC = 0.81, SE = 0.11; P < 0.005). Conclusion: Machine learning of computer-extracted texture features on gray-scale ultrasound images showed promising results classifying indeterminate thyroid nodules according to their surgical pathology.

1 April 2019 in Endocrine Practice
Verified
Journal Article
Closed access
KMKelvin Onyeka Memeh
Kelvin Onyeka Memeh
JPJeannine Esther Palacios
Jeannine Esther Palacios
RKRihan Khan
Rihan Khan
MGMarlon Alex Guerrero
Marlon Alex Guerrero

1 January 2021 in Surgery
Verified
Journal Article
Closed access
KMKelvin Memeh
Kelvin Memeh
BRBrian Ruhle
Brian Ruhle
TVTanaz Vaghaiwalla
Tanaz Vaghaiwalla
EKEdwin Kaplan
Edwin Kaplan
XKXavier Keutgen
Xavier Keutgen
PAPeter Angelos
Peter Angelos

26 August 2022 in Surgery
Verified
Journal Article
Closed access
BHBailey M. Humphreys
Bailey M. Humphreys
KMKelvin O. Memeh
Kelvin O. Memeh
AFAlex Funkhouser
Alex Funkhouser
TVTanaz Vaghaiwalla
Tanaz Vaghaiwalla

15 July 2022 in Annals of Surgery
Verified
Journal Article
Closed access
KMKelvin Md Memeh
Kelvin Md Memeh
TVTanaz Vaghaiwalla
Tanaz Vaghaiwalla
XKXavier Keutgen
Xavier Keutgen
PAPeter Angelos
Peter Angelos
Objective: To evaluate the relationship between the use intraoperative neuromonitoring (IONM) during thyroidectomy and the risk of recurrent laryngeal nerve (RLN) injury. Background: The role of IONM in reducing RLN injury during thyroidectomy remains controversial. Several studies on this topic apply conventional multivariable regression to adjust for confounding. However, estimates from this method may be biased due to model misspecification, especially with a rare outcome such as RLN injury. Methods: We used a pooled dataset created by linking the 2016–2019 National Surgical Quality Improvement Project General Participant User File with the corresponding Targeted-Thyroidectomy file. The primary outcome was RLN injury rates, and the secondary outcomes were operating time and postoperative length of stay. A doubly robust (DR) estimator, in the form of an inverse-probability-weighted regression adjustment model, was used to estimate the effect of the use of IONM on the risk of RLN injury. Sensitivity analyses was performed. Results: Twenty-four thousand three hundred seventy patients were evaluated, out of which 15,836 (70%) patients had IONM during thyroidectomy, and RLN injury occurred in 1498 (6.2%) cases. Rates of RLN injury increase with increasing age and BMI and are higher in patients with a cancer diagnosis, previous neck operation, total thyroidectomy, and node dissection. Doubly robust model suggests that the use of IONM was associated with a significant reduction in overall rate of RLN injury [risk ratio 0.77, confidence interval (CI), 0.68-0.87, P<0.001], and postoperative length of stay [−2.5 hours (CI, −4.18 to −0.81 h), P=0.004]. However, IONM use was associated with an increase in operating time [15.41 minutes (CI, 13.29-17.54 minutes), P<0.0001]. Sensitivity analyses revealed that our estimates are largely robust to confounding. Conclusion: In a balanced cohort of patients undergoing thyroidectomy from multiple sites and surgeons participating in National Surgical Quality Improvement Project, the use of IONM during thyroidectomy was associated with reduction in RLN injury.

1 January 2021 in Surgery
Verified
Journal Article
Closed access
TVTanaz Vaghaiwalla
Tanaz Vaghaiwalla
BRBrian Ruhle
Brian Ruhle
KMKelvin Memeh
Kelvin Memeh
PAPeter Angelos
Peter Angelos
EKEdwin Kaplan
Edwin Kaplan
XKXavier Keutgen
Xavier Keutgen