Emily Feld
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
Emily Feld has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
- Leora Horn
Vanderbilt University Medical Center, Nashville, TN
3 shared publications - Abigail Doucette
Abramson Cancer Center, University of Pennsylvania, Philadelphia, PA
2 shared publications - Anh N. Le
Division of Hematology-Oncology, Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania, USA
2 shared publications - Danielle Lee Mowery
University of Pennsylvania
2 shared publications - Douglas Buckner Johnson
Vanderbilt University Medical Center, Nashville, USA
2 shared publications - Emily Schriver
Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, United States
2 shared publications
Latest Publications
- Open Access
- 2 July 2021
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 7 (3) , e27970
A Natural Language Processing–Assisted Extraction System for Gleason Scores: Development and Usability Study
Background: Natural language processing (NLP) offers significantly faster variable extraction compared to traditional human extraction but cannot interpret complicated notes as well as humans can. Thus, we hypothesized that an “NLP-assisted” extraction system, which uses humans for complicated notes and NLP for uncomplicated notes, could produce faster extraction without compromising accuracy. Objective: The aim of this study was to develop and pilot an NLP-assisted extraction system to leverage the strengths of both human and NLP extraction of prostate cancer Gleason scores. Methods: We collected all available clinical and pathology notes for prostate cancer patients in an unselected academic biobank cohort. We developed an NLP system to extract prostate cancer Gleason scores from both clinical and pathology notes. Next, we designed and implemented the NLP-assisted extraction system algorithm to categorize notes into “uncomplicated” and “complicated” notes. Uncomplicated notes were assigned to NLP extraction and complicated notes were assigned to human extraction. We randomly reviewed 200 patients to assess the accuracy and speed of our NLP-assisted extraction system and compared it to NLP extraction alone and human extraction alone. Results: Of the 2051 patients in our cohort, the NLP system extracted a prostate surgery Gleason score from 1147 (55.92%) patients and a prostate biopsy Gleason score from 1624 (79.18%) patients. Our NLP-assisted extraction system had an overall accuracy rate of 98.7%, which was similar to the accuracy of human extraction alone (97.5%; P=.17) and significantly higher than the accuracy of NLP extraction alone (95.3%; P<.001). Moreover, our NLP-assisted extraction system reduced the workload of human extractors by approximately 95%, resulting in an average extraction time of 12.7 seconds per patient (vs 256.1 seconds per patient for human extraction alone). Conclusions: We demonstrated that an NLP-assisted extraction system was able to achieve much faster Gleason score extraction compared to traditional human extraction without sacrificing accuracy.
- 2 July 2021
- Published by JMIR Publications Inc. in JMIR Cancer
- Vol. 7 (3) , e27970
Open AccessA Natural Language Processing–Assisted Extraction System for Gleason Scores: Development and Usability Study
Background: Natural language processing (NLP) offers significantly faster variable extraction compared to traditional human extraction but cannot interpret complicated notes as well as humans can. Thus, we hypothesized that an “NLP-assisted” extraction system, which uses humans for complicated notes and NLP for uncomplicated notes, could produce faster extraction without compromising accuracy. Objective: The aim of this study was to develop and pilot an NLP-assisted extraction system to leverage the strengths of both human and NLP extraction of prostate cancer Gleason scores. Methods: We collected all available clinical and pathology notes for prostate cancer patients in an unselected academic biobank cohort. We developed an NLP system to extract prostate cancer Gleason scores from both clinical and pathology notes. Next, we designed and implemented the NLP-assisted extraction system algorithm to categorize notes into “uncomplicated” and “complicated” notes. Uncomplicated notes were assigned to NLP extraction and complicated notes were assigned to human extraction. We randomly reviewed 200 patients to assess the accuracy and speed of our NLP-assisted extraction system and compared it to NLP extraction alone and human extraction alone. Results: Of the 2051 patients in our cohort, the NLP system extracted a prostate surgery Gleason score from 1147 (55.92%) patients and a prostate biopsy Gleason score from 1624 (79.18%) patients. Our NLP-assisted extraction system had an overall accuracy rate of 98.7%, which was similar to the accuracy of human extraction alone (97.5%; P=.17) and significantly higher than the accuracy of NLP extraction alone (95.3%; P<.001). Moreover, our NLP-assisted extraction system reduced the workload of human extractors by approximately 95%, resulting in an average extraction time of 12.7 seconds per patient (vs 256.1 seconds per patient for human extraction alone). Conclusions: We demonstrated that an NLP-assisted extraction system was able to achieve much faster Gleason score extraction compared to traditional human extraction without sacrificing accuracy.
- Open Access
- 15 February 2021
- Published by JMIR Publications Inc. in JMIR Preprints
A Natural Language Processing–Assisted Extraction System for Gleason Scores: Development and Usability Study (Preprint)
BACKGROUND Natural language processing (NLP) offers significantly faster variable extraction compared to traditional human extraction but cannot interpret complicated notes as well as humans can. Thus, we hypothesized that an “NLP-assisted” extraction system, which uses humans for complicated notes and NLP for uncomplicated notes, could produce faster extraction without compromising accuracy. OBJECTIVE The aim of this study was to develop and pilot an NLP-assisted extraction system to leverage the strengths of both human and NLP extraction of prostate cancer Gleason scores. METHODS We collected all available clinical and pathology notes for prostate cancer patients in an unselected academic biobank cohort. We developed an NLP system to extract prostate cancer Gleason scores from both clinical and pathology notes. Next, we designed and implemented the NLP-assisted extraction system algorithm to categorize notes into “uncomplicated” and “complicated” notes. Uncomplicated notes were assigned to NLP extraction and complicated notes were assigned to human extraction. We randomly reviewed 200 patients to assess the accuracy and speed of our NLP-assisted extraction system and compared it to NLP extraction alone and human extraction alone. RESULTS Of the 2051 patients in our cohort, the NLP system extracted a prostate surgery Gleason score from 1147 (55.92%) patients and a prostate biopsy Gleason score from 1624 (79.18%) patients. Our NLP-assisted extraction system had an overall accuracy rate of 98.7%, which was similar to the accuracy of human extraction alone (97.5%; P=.17) and significantly higher than the accuracy of NLP extraction alone (95.3%; P<.001). Moreover, our NLP-assisted extraction system reduced the workload of human extractors by approximately 95%, resulting in an average extraction time of 12.7 seconds per patient (vs 256.1 seconds per patient for human extraction alone). CONCLUSIONS We demonstrated that an NLP-assisted extraction system was able to achieve much faster Gleason score extraction compared to traditional human extraction without sacrificing accuracy.
- 15 February 2021
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessA Natural Language Processing–Assisted Extraction System for Gleason Scores: Development and Usability Study (Preprint)
BACKGROUND Natural language processing (NLP) offers significantly faster variable extraction compared to traditional human extraction but cannot interpret complicated notes as well as humans can. Thus, we hypothesized that an “NLP-assisted” extraction system, which uses humans for complicated notes and NLP for uncomplicated notes, could produce faster extraction without compromising accuracy. OBJECTIVE The aim of this study was to develop and pilot an NLP-assisted extraction system to leverage the strengths of both human and NLP extraction of prostate cancer Gleason scores. METHODS We collected all available clinical and pathology notes for prostate cancer patients in an unselected academic biobank cohort. We developed an NLP system to extract prostate cancer Gleason scores from both clinical and pathology notes. Next, we designed and implemented the NLP-assisted extraction system algorithm to categorize notes into “uncomplicated” and “complicated” notes. Uncomplicated notes were assigned to NLP extraction and complicated notes were assigned to human extraction. We randomly reviewed 200 patients to assess the accuracy and speed of our NLP-assisted extraction system and compared it to NLP extraction alone and human extraction alone. RESULTS Of the 2051 patients in our cohort, the NLP system extracted a prostate surgery Gleason score from 1147 (55.92%) patients and a prostate biopsy Gleason score from 1624 (79.18%) patients. Our NLP-assisted extraction system had an overall accuracy rate of 98.7%, which was similar to the accuracy of human extraction alone (97.5%; P=.17) and significantly higher than the accuracy of NLP extraction alone (95.3%; P<.001). Moreover, our NLP-assisted extraction system reduced the workload of human extractors by approximately 95%, resulting in an average extraction time of 12.7 seconds per patient (vs 256.1 seconds per patient for human extraction alone). CONCLUSIONS We demonstrated that an NLP-assisted extraction system was able to achieve much faster Gleason score extraction compared to traditional human extraction without sacrificing accuracy.
- 1 January 2020
- Published by Elsevier in Practical Radiation Oncology
- Vol. 10 (1) , e50-e52
Radiation Recall Myositis After Carboplatin/Docetaxel Chemotherapy
- 1 January 2020
- Published by Elsevier in Practical Radiation Oncology
- Vol. 10 (1) , e50-e52
Radiation Recall Myositis After Carboplatin/Docetaxel Chemotherapy
- 16 December 2019
- Published by Taylor & Francis in Future Oncology
- Vol. 16 (2) , 4341-4345
First-line immune checkpoint inhibitor use in cisplatin-eligible patients with advanced urothelial carcinoma: a secular trend analysis
Aim: Standard first-line treatment of advanced urothelial cell carcinoma involves cisplatin-based chemotherapy, with carboplatin or immune checkpoint inhibitor therapy (ICI) reserved for cisplatin-...
- 16 December 2019
- Published by Taylor & Francis in Future Oncology
- Vol. 16 (2) , 4341-4345
First-line immune checkpoint inhibitor use in cisplatin-eligible patients with advanced urothelial carcinoma: a secular trend analysis
Aim: Standard first-line treatment of advanced urothelial cell carcinoma involves cisplatin-based chemotherapy, with carboplatin or immune checkpoint inhibitor therapy (ICI) reserved for cisplatin-...
- 1 October 2019
- Published by Elsevier in European Urology
- Vol. 76 (4) , 524-532
Effectiveness of First-line Immune Checkpoint Blockade Versus Carboplatin-based Chemotherapy for Metastatic Urothelial Cancer
- 1 October 2019
- Published by Elsevier in European Urology
- Vol. 76 (4) , 524-532
Effectiveness of First-line Immune Checkpoint Blockade Versus Carboplatin-based Chemotherapy for Metastatic Urothelial Cancer
- 1 May 2019
- Published by Elsevier in Clinical Lung Cancer
- Vol. 20 (3) , e291-e298
Palliative Care Referrals for Advanced Non–small-cell Lung Cancer (NSCLC): Patient and Provider Attitudes and Practices
- 1 May 2019
- Published by Elsevier in Clinical Lung Cancer
- Vol. 20 (3) , e291-e298
Palliative Care Referrals for Advanced Non–small-cell Lung Cancer (NSCLC): Patient and Provider Attitudes and Practices
- 28 August 2018
- Published by Taylor & Francis in Immunotherapy
- Vol. 10 (11) , 987-998
Immunotherapy in Melanoma
Immunotherapy has dramatically improved the prognosis for patients with melanoma and has become the cornerstone of treatment for those with advanced disease. The role of immunotherapy continues to expand with multiple new agents approved in the adjuvant as well as metastatic setting, as first-line therapy and beyond. We review the currently approved drugs for the treatment of melanoma, along with clinical trial data, adverse side effects, response assessment and future directions.
- 28 August 2018
- Published by Taylor & Francis in Immunotherapy
- Vol. 10 (11) , 987-998
Immunotherapy in Melanoma
Immunotherapy has dramatically improved the prognosis for patients with melanoma and has become the cornerstone of treatment for those with advanced disease. The role of immunotherapy continues to expand with multiple new agents approved in the adjuvant as well as metastatic setting, as first-line therapy and beyond. We review the currently approved drugs for the treatment of melanoma, along with clinical trial data, adverse side effects, response assessment and future directions.
- Open Access
- 1 July 2017
- Published by Taylor & Francis in OncoTargets and Therapy
- Vol. ume 10, 3697-3708
Emerging role of nivolumab in the management of patients with non-small-cell lung cancer: current data and future perspectives
Immune-checkpoint inhibitors have become valuable therapies in the treatment of patients with non-small-cell lung cancer (NSCLC). Recent clinical trials have shown promising results with regard to efficacy and toxicity profiles of these agents compared to cytotoxic chemotherapy. Nivolumab was one of the first immune-checkpoint inhibitors to demonstrate clinical activity in patients with NSCLC, and is currently approved in the US for treatment of patients with advanced squamous and nonsquamous NSCLC who have progressed on or after platinum-based chemotherapy. This review provides an update on nivolumab’s pharmacology, safety, and efficacy, as established by the CheckMate trials. We also discuss specific applications and strategies for the use of nivolumab in NSCLC patients, as well as predictive biomarkers and their role in treatment selection.
- 1 July 2017
- Published by Taylor & Francis in OncoTargets and Therapy
- Vol. ume 10, 3697-3708
Open AccessEmerging role of nivolumab in the management of patients with non-small-cell lung cancer: current data and future perspectives
Immune-checkpoint inhibitors have become valuable therapies in the treatment of patients with non-small-cell lung cancer (NSCLC). Recent clinical trials have shown promising results with regard to efficacy and toxicity profiles of these agents compared to cytotoxic chemotherapy. Nivolumab was one of the first immune-checkpoint inhibitors to demonstrate clinical activity in patients with NSCLC, and is currently approved in the US for treatment of patients with advanced squamous and nonsquamous NSCLC who have progressed on or after platinum-based chemotherapy. This review provides an update on nivolumab’s pharmacology, safety, and efficacy, as established by the CheckMate trials. We also discuss specific applications and strategies for the use of nivolumab in NSCLC patients, as well as predictive biomarkers and their role in treatment selection.
- 1 April 2017
- Published by Elsevier in Journal of Thoracic Oncology
- Vol. 12 (4) , 612-623
Driven by Mutations: The Predictive Value of Mutation Subtype in EGFR -Mutated Non–Small Cell Lung Cancer
- 1 April 2017
- Published by Elsevier in Journal of Thoracic Oncology
- Vol. 12 (4) , 612-623
Driven by Mutations: The Predictive Value of Mutation Subtype in EGFR -Mutated Non–Small Cell Lung Cancer
- 1 January 2017
- Published by Wolters Kluwer Health in Journal of Immunotherapy
- Vol. 40 (1) , 31-35
Sequencing Treatment in BRAF V600 Mutant Melanoma: Anti-PD-1 Before and After BRAF Inhibition
Novel agents targeting immune checkpoint molecules or mutated BRAF are active therapeutic options for patients with BRAF V600-mutant melanoma. However, the most effective first-line treatment and the optimal sequencing of these agents have not been well characterized. To explore this, we retrospectively assessed 114 patients from 4 centers with advanced, BRAF V600-mutant melanoma who received anti-programmed cell death-1 (PD-1)/PD-L1 antibodies. We evaluated clinical outcomes, including objective response rate (ORR), overall survival (OS), and progression-free survival (PFS) to initial and subsequent therapies in patients that received anti-PD-1 first (n=56) versus those that received BRAF±MEK inhibitors (BRAFi) first (n=58). Median OS was similar between these groups (27.5 vs. 40.3 mo, P=0.71). Patients who progressed on anti-PD-1 during the study timeframe had worse outcomes after starting subsequent BRAFi than those who had not received prior anti-PD-1 (median PFS 5 vs. 7.4 mo, median OS 10.6 vs. 40.3 mo). Similarly, patients who previously progressed on BRAFi had seemingly inferior outcomes after starting anti-PD-1 compared with those without prior BRAFi, including ORR (25% vs. 41%), median PFS (2.8 vs. 10.6 mo) and median OS (8.2 vs. 27.6 mo). Notably, patients who benefited >6 months from BRAFi had superior ORR to subsequent anti-PD-1 compared with those with more rapid progression (P=0.04). We conclude that either BRAFi or anti-PD-1 may be effective regardless of treatment sequence in patients with BRAF V600-mutant melanoma, but clinical outcomes to front-line therapy are superior. In addition, we suggest a shared “responder phenotype” between BRAFi and anti-PD-1.
- 1 January 2017
- Published by Wolters Kluwer Health in Journal of Immunotherapy
- Vol. 40 (1) , 31-35
Sequencing Treatment in BRAF V600 Mutant Melanoma: Anti-PD-1 Before and After BRAF Inhibition
Novel agents targeting immune checkpoint molecules or mutated BRAF are active therapeutic options for patients with BRAF V600-mutant melanoma. However, the most effective first-line treatment and the optimal sequencing of these agents have not been well characterized. To explore this, we retrospectively assessed 114 patients from 4 centers with advanced, BRAF V600-mutant melanoma who received anti-programmed cell death-1 (PD-1)/PD-L1 antibodies. We evaluated clinical outcomes, including objective response rate (ORR), overall survival (OS), and progression-free survival (PFS) to initial and subsequent therapies in patients that received anti-PD-1 first (n=56) versus those that received BRAF±MEK inhibitors (BRAFi) first (n=58). Median OS was similar between these groups (27.5 vs. 40.3 mo, P=0.71). Patients who progressed on anti-PD-1 during the study timeframe had worse outcomes after starting subsequent BRAFi than those who had not received prior anti-PD-1 (median PFS 5 vs. 7.4 mo, median OS 10.6 vs. 40.3 mo). Similarly, patients who previously progressed on BRAFi had seemingly inferior outcomes after starting anti-PD-1 compared with those without prior BRAFi, including ORR (25% vs. 41%), median PFS (2.8 vs. 10.6 mo) and median OS (8.2 vs. 27.6 mo). Notably, patients who benefited >6 months from BRAFi had superior ORR to subsequent anti-PD-1 compared with those with more rapid progression (P=0.04). We conclude that either BRAFi or anti-PD-1 may be effective regardless of treatment sequence in patients with BRAF V600-mutant melanoma, but clinical outcomes to front-line therapy are superior. In addition, we suggest a shared “responder phenotype” between BRAFi and anti-PD-1.