Adam Ostrovsky

Mr. Adam Ostrovsky

Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, Mississippi, USA
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
1 November 2020 in Journal of Adolescent Health
Verified
Journal Article
Closed access
AOAdam Ostrovsky
Adam Ostrovsky
JCJoshua R. Chen
Joshua R. Chen

30 March 2025 in The American Journal of Emergency Medicine
Verified
Journal Article
Open access
AOAdam Ostrovsky
Adam Ostrovsky
The rapid advancement of artificial intelligence (AI) has great ability to impact healthcare. Chest X-rays are essential for diagnosing acute thoracic conditions in the emergency department (ED), but interpretation delays due to radiologist availability can impact clinical decision-making. AI models, including deep learning algorithms, have been explored for diagnostic support, but the potential of large language models (LLMs) in emergency radiology remains largely unexamined. This study assessed ChatGPT's feasibility in interpreting chest X-rays for acute thoracic conditions commonly encountered in the ED. A subset of 1400 images from the NIH Chest X-ray dataset was analyzed, representing seven pathology categories: Atelectasis, Effusion, Emphysema, Pneumothorax, Pneumonia, Mass, and No Finding. ChatGPT 4.0, utilizing the "X-Ray Interpreter" add-on, was evaluated for its diagnostic performance across these categories. ChatGPT demonstrated high performance in identifying normal chest X-rays, with a sensitivity of 98.9 %, specificity of 93.9 %, and accuracy of 94.7 %. However, the model's performance varied across pathologies. The best results were observed in diagnosing pneumonia (sensitivity 76.2 %, specificity 93.7 %) and pneumothorax (sensitivity 77.4 %, specificity 89.1 %), while performance for atelectasis and emphysema was lower. ChatGPT demonstrates potential as a supplementary tool for differentiating normal from abnormal chest X-rays, with promising results for certain pathologies like pneumonia. However, its diagnostic accuracy for more subtle conditions requires improvement. Further research integrating ChatGPT with specialized image recognition models could enhance its performance, offering new possibilities in medical imaging and education.

5 June 2024 in Mayo Clinic Proceedings: Digital Health
Verified
Journal Article
Open access
AOAdam Ostrovsky
Adam Ostrovsky
JCJoshua R. Chen
Joshua R. Chen
VSVishal N. Shah
Vishal N. Shah
BABabak Abai
Babak Abai

Verified
Journal Article
Open access
PDF file
AOAdam Ostrovsky
Adam Ostrovsky
ZPZachary James Prebay
Zachary James Prebay
PCPaul H Chung
Paul H Chung
Background: How quickly providers adapt to new practice guidelines is not well known. The objective of this study was to evaluate temporal trends in the performance of urethral endoscopic management and urethroplasty surrounding the release of the American Urological Association (AUA) Male Urethral Stricture Guidelines in 2017. We also evaluate in parallel trends in female urethral stricture disease, where AUA guidelines are not present. We hypothesized that the ratio of urethroplasty versus urethral endoscopic management in both males and females is increasing and that guidelines do not result in immediate changes in management trends. Methods: Endoscopic management and urethroplasty data were collected from the TriNetX database on adult males and females five years before (starting 1 January 2012) and after (ending 31 December 2022) the 2017 AUA guidelines. Cohorts were built using Current Procedural Terminology (CPT) codes and grouped into urethral endoscopic management (Males: CPT 52275, 52281, 52282, 53600, 53601, 53620, 53621; Females: CPT 52270, 53660, 53661, 53665) or urethroplasty (Males: CPT 53000, 53010, 53400, 53410, 53415, 53420, 53450, 53460; Females: CPT 53430). Data on patient age, race, and geographic distribution were also collected. Results: In total, 27,623 (Males: 25,039; Females: 2584) endoscopic managements and 11,771 (Males: 11,105; Females: 666) urethroplasties were reviewed across 51 Health Care Organizations. The mean age of endoscopic management and urethroplasty patients was 67.1 and 55.7, respectively (p < 0.01). The urethroplasty-to-endoscopic management ratio decreased for males between 2012 and 2013 and then steadily increased until 2017. The ratio steadily increased for females from 2012 to 2017. The urethroplasty-to-endoscopic management ratio showed a slight decline from 2017 to 2020 across both males and females before rising again through 2022 to a study high (Males: 0.62; Females: 0.63). Regional differences were identified, with the West having the highest urethroplasty-to-endoscopic management ratios for both males and females, the Northeast having the lowest urethroplasty-to-endoscopic management ratio for males, and the Midwest having the lowest ratio for females. Conclusions: The utilization of urethroplasty for males and females is increasing. An immediate benefit on post-guideline urethroplasty rates was not observed, and the utilization of female urethroplasty increased despite the absence of AUA guidelines. These illustrate that the impact of guideline dissemination takes time and supports the need for continued provider outreach and education on urethral stricture disease and management.

Verified
Journal Article
Open access
PDF file
ZPZachary James Prebay
Zachary James Prebay
AOAdam Ostrovsky
Adam Ostrovsky
MBMatthew Buck
Matthew Buck
PCPaul H Chung
Paul H Chung
Background: We queried a global database to understand re-intervention rates following urethroplasty with the goal of evaluating whether they align with previously published data. Methods: Using the TriNetX database and Common Procedural Terminology (CPT) and International Classification of Diseases-10 (ICD) codes, we identified adult male patients with urethral stricture disease (ICD N35) who underwent one-stage anterior (CPT 53410) or posterior urethroplasty (CPT 53415), with or without (substitution urethroplasty) a tissue flap (CPT 15740) or buccal graft (CPT 15240 or 15241). We set urethroplasty as the index event and used descriptive statistics to report the incidence of secondary procedures (using CPT codes) within 10 years after the index event. Results: There were 6606 patients who underwent urethroplasty within the last 20 years, with 14.3% of patients undergoing a second procedure after index event. Upon subgroup analysis, reintervention rates were 14.5% for anterior urethroplasty vs. 12.4% of patients with an anterior substitution urethroplasty (RR 1.7, p = 0.09) and 13.3% for posterior urethroplasty vs. 8.2% for patients with a posterior substitution urethroplasty (RR 1.6, p < 0.01). Conclusions: Most patients will not need any form of re-intervention following urethroplasty. These data align with previously described recurrence rates, which may help urologists counsel patients considering urethroplasty.

1 January 2023 in Journal of Patient Experience
Verified
Journal Article
Open access
CPChitra Parikh
Chitra Parikh
AOAdam Ostrovsky
Adam Ostrovsky
This study aims to determine the readability and trustworthiness of English and Spanish hypo- and hyperthyroid-related online information. Google searches were conducted for four search terms: hypothyroidism, Hashimoto's Disease, hyperthyroidism, and Graves’ Disease. For each search term, the first 10 websites were analyzed with a total of 40 websites analyzed. Readability formulas were used to determine English and Spanish readability. Trustworthiness was determined using HONcode status, JAMA Benchmark Criteria, and NLM Trustworthy Score. Overall readability largely exceeded recommended grade levels. Only 1 website (2.5%) presented information below the eighth-grade reading level based on overall Readability Consensus score, while 31 websites (77.5%) exceeded this threshold for all measures. The mean (SD) English readability grade level was 9.6 (3.44); the mean (SD) Spanish grade was 8.5 (4.58). No significant relationships were found between the JAMA Benchmark Criteria, NLM Trustworthy Score, HONcode status, and readability. 67.5% of websites analyzed (n = 27) were certified with the Health on the Net Foundation's code of conduct. Websites about common thyroid-related conditions have overall poor readability. The availability of resources for Spanish-speaking patients is also poor. Steps should be taken to ensure that online health-related materials are comprehensible. Physicians should recognize that patients may have few trustworthy and easy-to-understand sources to access information. The readability and trustworthiness of sources should be considered when providing patients suggested sources for further reading. It may be particularly helpful for physicians to utilize websites with favorable readability scores such as the American Thyroid Association website.