Derek E. Smith
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Derek E. Smith has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- David Ross Camidge
University of Colorado Cancer Center, Aurora, CO 80045, USA
2 shared publications - Terry Ng
Department of Medicine, Division of Medical Oncology, The Ottawa Hospital, University of Ottawa, Ottawa, ON K1H 8L6, Canada
2 shared publications - Adrie van Bokhoven
Department of Pathology, University of Colorado Anschutz Medical Campus, Aurora, CO 80045, USA
1 shared publication Amanda Tompkins
Department of Medicine, Division of Gastroenterology and Hepatology, University of Colorado Anschutz Medical Campus, Aurora, USA
1 shared publication- Anna E. Baron
Department of Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO
1 shared publication Anna E. Barón
Department of Biostatistics and Informatics, Colorado School of Public Health, University of Colorado, Anschutz Medical Campus, Aurora, Colorado
1 shared publication
Latest Publications
- 27 May 2022
- Published by Springer Nature in Digestive Diseases and Sciences
- Vol. 68 (1) , 240-251
Adoption of Optimal Small (6–9 mm) Colorectal Polyp Resection Technique Over Time
Background Cold snare polypectomy (CSP) is the preferred resection technique for small (6–9 mm) polyps due to lower rate of incomplete resection compared to cold forceps polypectomy (CFP) and improved safety profile over hot snare polypectomy (HSP). Aims To describe resection techniques for small (6–9 mm) polyps and determine factors associated with sub-optimal technique. Methods This was retrospective cohort study of colonoscopies performed by gastroenterological and surgical endoscopists from 2012 to 2019 where at least one 6–9 mm polyp was removed. Patient, provider, and procedure characteristics were collected. Univariate and multivariate regression analyses were performed to determine factors associated with sub-optimal technique. Results In total, 773 colonoscopies where 1,360 6–9 mm polyps removed by 21 endoscopists were included. CSP was used for 1,122 (82.5%), CFP for 61 (4.5%), and HSP for 177 (13.0%). Surgeon specialty was associated with CFP use (aOR 7.81; 95% CI 3.02–20.16). Polyp location in left colon (aOR 1.65; 95% CI 1.17–2.33) and pedunculated morphology (aOR 12.76; 95% CI 7.24–22.50) were associated with HSP. There was a significant increase in overall CSP use from 30.4% in 2012 to 96.8% in 2019. Conclusions 82.5% of all 6–9 mm polyps removed from 2012 to 2019 were removed using a cold snare with significant increase in CSP from 2012 to 2019. Differences in how optimal technique was adopted over time based on specialty highlight the need for standardized practice guidelines and quality monitoring.
- 27 May 2022
- Published by Springer Nature in Digestive Diseases and Sciences
- Vol. 68 (1) , 240-251
Adoption of Optimal Small (6–9 mm) Colorectal Polyp Resection Technique Over Time
Background Cold snare polypectomy (CSP) is the preferred resection technique for small (6–9 mm) polyps due to lower rate of incomplete resection compared to cold forceps polypectomy (CFP) and improved safety profile over hot snare polypectomy (HSP). Aims To describe resection techniques for small (6–9 mm) polyps and determine factors associated with sub-optimal technique. Methods This was retrospective cohort study of colonoscopies performed by gastroenterological and surgical endoscopists from 2012 to 2019 where at least one 6–9 mm polyp was removed. Patient, provider, and procedure characteristics were collected. Univariate and multivariate regression analyses were performed to determine factors associated with sub-optimal technique. Results In total, 773 colonoscopies where 1,360 6–9 mm polyps removed by 21 endoscopists were included. CSP was used for 1,122 (82.5%), CFP for 61 (4.5%), and HSP for 177 (13.0%). Surgeon specialty was associated with CFP use (aOR 7.81; 95% CI 3.02–20.16). Polyp location in left colon (aOR 1.65; 95% CI 1.17–2.33) and pedunculated morphology (aOR 12.76; 95% CI 7.24–22.50) were associated with HSP. There was a significant increase in overall CSP use from 30.4% in 2012 to 96.8% in 2019. Conclusions 82.5% of all 6–9 mm polyps removed from 2012 to 2019 were removed using a cold snare with significant increase in CSP from 2012 to 2019. Differences in how optimal technique was adopted over time based on specialty highlight the need for standardized practice guidelines and quality monitoring.
- Open Access
Development of a Prediction Model for Incident Atrial Fibrillation using Machine Learning Applied to Harmonized Electronic Health Record Data
Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, whose early detection could lead to significant improvements in outcomes through appropriate prescription of anticoagulation. Although a variety of methods exist for screening for AF, there is general agreement that a targeted approach would be preferred. Implicit within this approach is the need for an efficient method for identification of patients at risk. In this investigation, we examined the strengths and weaknesses of an approach based on application of machine-learning algorithms to electronic health record (EHR) data that has been harmonized to the Observational Medical Outcomes Partnership (OMOP) common data model. We examined data from a total of 2.3M individuals, of whom 1.16% developed incident AF over designated 6-month time intervals. We examined and compared several approaches for data reduction, sample balancing (re-sampling) and predictive modeling using cross-validation for hyperparameter selection, and out-of-sample testing for validation. Although no approach provided outstanding classification accuracy, we found that the optimal approach for prediction of 6-month incident AF used a random forest classifier, raw features (no data reduction), and synthetic minority oversampling technique (SMOTE) resampling (F 1 statistic 0.12, AUC 0.65). This model performed better than a predictive model based only on known AF risk factors, and highlighted the importance of using resampling methods to optimize ML approaches to imbalanced data as exists in EHRs. Further studies using EHR data in other medical systems are needed to validate the clinical applicability of these findings.
Open AccessDevelopment of a Prediction Model for Incident Atrial Fibrillation using Machine Learning Applied to Harmonized Electronic Health Record Data
Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia, whose early detection could lead to significant improvements in outcomes through appropriate prescription of anticoagulation. Although a variety of methods exist for screening for AF, there is general agreement that a targeted approach would be preferred. Implicit within this approach is the need for an efficient method for identification of patients at risk. In this investigation, we examined the strengths and weaknesses of an approach based on application of machine-learning algorithms to electronic health record (EHR) data that has been harmonized to the Observational Medical Outcomes Partnership (OMOP) common data model. We examined data from a total of 2.3M individuals, of whom 1.16% developed incident AF over designated 6-month time intervals. We examined and compared several approaches for data reduction, sample balancing (re-sampling) and predictive modeling using cross-validation for hyperparameter selection, and out-of-sample testing for validation. Although no approach provided outstanding classification accuracy, we found that the optimal approach for prediction of 6-month incident AF used a random forest classifier, raw features (no data reduction), and synthetic minority oversampling technique (SMOTE) resampling (F 1 statistic 0.12, AUC 0.65). This model performed better than a predictive model based only on known AF risk factors, and highlighted the importance of using resampling methods to optimize ML approaches to imbalanced data as exists in EHRs. Further studies using EHR data in other medical systems are needed to validate the clinical applicability of these findings.
- 1 January 2019
- Published by Elsevier in Clinical Lung Cancer
- Vol. 20 (1) , e39-e51
Preselection of Lung Cancer Cases Using FGFR1 mRNA and Gene Copy Number for Treatment With Ponatinib
- 1 January 2019
- Published by Elsevier in Clinical Lung Cancer
- Vol. 20 (1) , e39-e51
Preselection of Lung Cancer Cases Using FGFR1 mRNA and Gene Copy Number for Treatment With Ponatinib
- 22 October 2018
- Published by Elsevier in Lung Cancer
- Vol. 126, 112-118
Detection of oligoprogressive disease in oncogene-addicted non-small cell lung cancer using PET/CT versus CT in patients receiving a tyrosine kinase inhibitor
- 22 October 2018
- Published by Elsevier in Lung Cancer
- Vol. 126, 112-118
Detection of oligoprogressive disease in oncogene-addicted non-small cell lung cancer using PET/CT versus CT in patients receiving a tyrosine kinase inhibitor
- 24 March 2018
- Published by Wiley in American Journal of Industrial Medicine
- Vol. 61 (7) , 592-604
Clinical and laboratory factors contributing to uninterpretable beryllium lymphocyte proliferation tests (BeLPT)
Background: The beryllium lymphocyte proliferation test (BeLPT), has become the principal clinical test for detecting beryllium sensitization and chronic beryllium disease. Uninterpretable BeLPT results can occur in a small but significant proportion of tests from poor lymphocyte growth (PG) or over proliferation of lymphocytes (OP). The clinical and laboratory causes of uninterpretable results are not known.Methods: BeLPT data from the US Department of Energy‐supported Former Worker Screening Program were analyzed for a 10‐year period. Drivers of uninterpretable BeLPTs were investigated using multivariable models and classification techniques.Results: Three participant attributes were significantly associated with PG, while OP showed no significant associations. Serum lot for the lymphocyte growth medium accounted for 21% of the variation in PG and 16% in OP.Conclusion: Serum lots influence the likelihood of having uninterpretable BeLPT. To better understand uninterpretable results and possibly reduce their occurrence, additional laboratory‐related factors should be addressed.
- 24 March 2018
- Published by Wiley in American Journal of Industrial Medicine
- Vol. 61 (7) , 592-604
Clinical and laboratory factors contributing to uninterpretable beryllium lymphocyte proliferation tests (BeLPT)
Background: The beryllium lymphocyte proliferation test (BeLPT), has become the principal clinical test for detecting beryllium sensitization and chronic beryllium disease. Uninterpretable BeLPT results can occur in a small but significant proportion of tests from poor lymphocyte growth (PG) or over proliferation of lymphocytes (OP). The clinical and laboratory causes of uninterpretable results are not known.Methods: BeLPT data from the US Department of Energy‐supported Former Worker Screening Program were analyzed for a 10‐year period. Drivers of uninterpretable BeLPTs were investigated using multivariable models and classification techniques.Results: Three participant attributes were significantly associated with PG, while OP showed no significant associations. Serum lot for the lymphocyte growth medium accounted for 21% of the variation in PG and 16% in OP.Conclusion: Serum lots influence the likelihood of having uninterpretable BeLPT. To better understand uninterpretable results and possibly reduce their occurrence, additional laboratory‐related factors should be addressed.
- 1 June 2016
- Published by Elsevier in Journal of Great Lakes Research
- Vol. 42 (3) , 608-618
Winter–spring diatom production in Lake Erie is an important driver of summer hypoxia
- 1 June 2016
- Published by Elsevier in Journal of Great Lakes Research
- Vol. 42 (3) , 608-618
Winter–spring diatom production in Lake Erie is an important driver of summer hypoxia
- 20 January 2011
- Published by Wiley in River Research and Applications
- Vol. 28 (7) , 1047-1053
SIZE-FRACTIONATED PHYTOPLANKTON GROWTH AND MICROZOOPLANKTON GRAZING RATES IN THE UPPER ST. LAWRENCE RIVER
- 20 January 2011
- Published by Wiley in River Research and Applications
- Vol. 28 (7) , 1047-1053
SIZE-FRACTIONATED PHYTOPLANKTON GROWTH AND MICROZOOPLANKTON GRAZING RATES IN THE UPPER ST. LAWRENCE RIVER
- 1 December 2005
- Published by Radiopaedia Australia Pty Ltd
Left M2 infarct (CT perfusion)
- 1 January 1997
- Published by EAGE Publications bv
Automated Quality Assessment of Seismic Data