Khashayar Eshaghi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Khashayar Eshaghi has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Abigail Doucette
Abramson Cancer Center, University of Pennsylvania, Philadelphia, PA
1 shared publication - Adam D. Cohen
Abramson Cancer Center and University of Pennsylvania, Philadelphia, USA
1 shared publication Adam J. Waxman
1 shared publication- Alberto Carturan
University of Pennsylvania, Philadelphia, Pennsylvania, USA
1 shared publication - Alfred L. Garfall
Division of Hematology-Oncology, Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, USA
1 shared publication - Ana I. Velazquez
University of California, San Francisco, CA
1 shared publication
Latest Publications
- 1 April 2026
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 10 (2) , e2600114
Gaps in Patient-Facing Information on Artificial Intelligence in Cancer Care: A Cross-Sectional Analysis
PURPOSE: Artificial intelligence (AI) is increasingly integrated into cancer care and accessible to patients, yet the quality and accessibility of patient-facing information on this topic are poorly characterized. We evaluated the quality, readability, and AI safety concept coverage of publicly available Webpages and YouTube videos that patients are likely to encounter when searching to learn about AI in cancer care. METHODS: We conducted a cross-sectional analysis of digital content identified using Google Trends–derived search terms on August 6, 2025. Two independent reviewers screened the first 170 Google and 150 YouTube results for patient-facing content relevant to AI in cancer care, with discrepancies resolved by a third reviewer. Information quality was assessed using DISCERN (scale 1-5; ≥4 = high quality). Webpage readability was evaluated using Flesch-Kincaid (FK), Gunning Fog (GF), and Simplified Measure of Gobbledygook (SMOG) indices. Coverage of AI safety concepts (hallucination risk, clinician oversight, bias/equity, transparency) was assessed. RESULTS: Of the 320 resources screened, 52 Webpages (31%) and 30 videos (20%) met inclusion criteria. Median DISCERN scores were 2.5 (IQR, 2.5-4.0) for Webpages and 2.25 (IQR, 1.5-3.0) for videos, indicating overall low-quality information. Only 17 Webpages (33%) and seven videos (23%) were of high quality. Median Webpage readability corresponded to college level across all indices (FK 12.5, GF 15.0, SMOG 14.3), exceeding the sixth- to eighth-grade reading level recommended by the American Medical Association and National Institutes of Health. Most Webpages addressed clinician oversight (79%) and transparency (79%), but few discussed hallucination risk (15%). CONCLUSION: Patient-facing online information about AI in cancer care is limited, low in quality, difficult to read, and frequently omits safety concepts, highlighting an urgent need for accessible, high-quality resources.
- 1 April 2026
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 10 (2) , e2600114
Gaps in Patient-Facing Information on Artificial Intelligence in Cancer Care: A Cross-Sectional Analysis
PURPOSE: Artificial intelligence (AI) is increasingly integrated into cancer care and accessible to patients, yet the quality and accessibility of patient-facing information on this topic are poorly characterized. We evaluated the quality, readability, and AI safety concept coverage of publicly available Webpages and YouTube videos that patients are likely to encounter when searching to learn about AI in cancer care. METHODS: We conducted a cross-sectional analysis of digital content identified using Google Trends–derived search terms on August 6, 2025. Two independent reviewers screened the first 170 Google and 150 YouTube results for patient-facing content relevant to AI in cancer care, with discrepancies resolved by a third reviewer. Information quality was assessed using DISCERN (scale 1-5; ≥4 = high quality). Webpage readability was evaluated using Flesch-Kincaid (FK), Gunning Fog (GF), and Simplified Measure of Gobbledygook (SMOG) indices. Coverage of AI safety concepts (hallucination risk, clinician oversight, bias/equity, transparency) was assessed. RESULTS: Of the 320 resources screened, 52 Webpages (31%) and 30 videos (20%) met inclusion criteria. Median DISCERN scores were 2.5 (IQR, 2.5-4.0) for Webpages and 2.25 (IQR, 1.5-3.0) for videos, indicating overall low-quality information. Only 17 Webpages (33%) and seven videos (23%) were of high quality. Median Webpage readability corresponded to college level across all indices (FK 12.5, GF 15.0, SMOG 14.3), exceeding the sixth- to eighth-grade reading level recommended by the American Medical Association and National Institutes of Health. Most Webpages addressed clinician oversight (79%) and transparency (79%), but few discussed hallucination risk (15%). CONCLUSION: Patient-facing online information about AI in cancer care is limited, low in quality, difficult to read, and frequently omits safety concepts, highlighting an urgent need for accessible, high-quality resources.
- Open Access
- 16 July 2025
- Published by Elsevier in Blood Immunology & Cellular Therapy
- Vol. 1 (2)
Access and outcomes of racial and ethnic minority populations receiving commercial anti-BCMA CART for myeloma
- 16 July 2025
- Published by Elsevier in Blood Immunology & Cellular Therapy
- Vol. 1 (2)
Open AccessAccess and outcomes of racial and ethnic minority populations receiving commercial anti-BCMA CART for myeloma
- Open Access
- 1 February 2025
- Published by Wolters Kluwer Health in Neurology Genetics
- Vol. 11 (1) , e200234
Genetic and Phenotypic Variability in Siblings With Friedreich Ataxia
Friedreich ataxia (FRDA) is an autosomal recessive disorder caused by FXN gene mutations involving GAA trinucleotide repeat expansions. This study explores phenotypic heterogeneity between siblings, focusing on differences in age at onset (AAO) and shorter GAA repeat (GAA1) length to improve understanding of disease variability. We analyzed AAO and genotype of siblings with FRDA. Linear regression examined AAO differences and genetic predictors (GAA1 length and SIRT6 S46N single nucleotide polymorphism), while logistic regression assessed discordant clinical manifestations and GAA1 heterogeneity. This study included 150 siblings with FRDA from 70 families. GAA1 and AAO differences between siblings were not significant, although discordance between siblings in the diagnosis of hypertrophic cardiomyopathy and scoliosis was noted in approximately a quarter of the families. Differences in GAA1 length predicted a modest amount of AAO heterogeneity (R2 = 0.075). The S46N polymorphism in SIRT6 did not predict the differences in AAO. Genetic and phenotypic variability between paired siblings with FRDA was moderate to small, with GAA1 differences explaining some of the variance in AAO. Other factors (genetic or environmental) or data collection bias may explain the remaining variance. These findings highlight the complexity of FRDA and reiterate the role of GAA1 length in disease severity.
- 1 February 2025
- Published by Wolters Kluwer Health in Neurology Genetics
- Vol. 11 (1) , e200234
Open AccessGenetic and Phenotypic Variability in Siblings With Friedreich Ataxia
Friedreich ataxia (FRDA) is an autosomal recessive disorder caused by FXN gene mutations involving GAA trinucleotide repeat expansions. This study explores phenotypic heterogeneity between siblings, focusing on differences in age at onset (AAO) and shorter GAA repeat (GAA1) length to improve understanding of disease variability. We analyzed AAO and genotype of siblings with FRDA. Linear regression examined AAO differences and genetic predictors (GAA1 length and SIRT6 S46N single nucleotide polymorphism), while logistic regression assessed discordant clinical manifestations and GAA1 heterogeneity. This study included 150 siblings with FRDA from 70 families. GAA1 and AAO differences between siblings were not significant, although discordance between siblings in the diagnosis of hypertrophic cardiomyopathy and scoliosis was noted in approximately a quarter of the families. Differences in GAA1 length predicted a modest amount of AAO heterogeneity (R2 = 0.075). The S46N polymorphism in SIRT6 did not predict the differences in AAO. Genetic and phenotypic variability between paired siblings with FRDA was moderate to small, with GAA1 differences explaining some of the variance in AAO. Other factors (genetic or environmental) or data collection bias may explain the remaining variance. These findings highlight the complexity of FRDA and reiterate the role of GAA1 length in disease severity.