Pradosh Kumar Sarangi

Pradosh Kumar Sarangi

Auto-generated profile, based on publicly available information

Pradosh Kumar Sarangi

Department of Radiodiagnosis, All India Institute of Medical Sciences, Deoghar, Jharkhand, India

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
29 December 2023 in Indian Journal of Radiology and Imaging
Verified
Journal Article
Open access
PDF file
PSPradosh Kumar Sarangi
Pradosh Kumar Sarangi
RNRavi Kant Narayan
Ravi Kant Narayan
SMSudipta Mohakud
Sudipta Mohakud
AVAditi Vats
Aditi Vats
DSDebabrata Sahani
Debabrata Sahani
Himel MondalHimel Mondal
Himel Mondal
Background The field of radiology relies on accurate interpretation of medical images for effective diagnosis and patient care. Recent advancements in artificial intelligence (AI) and natural language processing have sparked interest in exploring the potential of AI models in assisting radiologists. However, limited research has been conducted to assess the performance of AI models in radiology case interpretation, particularly in comparison to human experts. Objective This study aimed to evaluate the performance of ChatGPT, Google Bard, and Bing in solving radiology case vignettes (Fellowship of the Royal College of Radiologists 2A [FRCR2A] examination style questions) by comparing their responses to those provided by two radiology residents. Methods A total of 120 multiple-choice questions based on radiology case vignettes were formulated according to the pattern of FRCR2A examination. The questions were presented to ChatGPT, Google Bard, and Bing. Two residents wrote the examination with the same questions in 3 hours. The responses generated by the AI models were collected and compared to the answer keys and explanation of the answers was rated by the two radiologists. A cutoff of 60% was set as the passing score. Results The two residents (63.33 and 57.5%) outperformed the three AI models: Bard (44.17%), Bing (53.33%), and ChatGPT (45%), but only one resident passed the examination. The response patterns among the five respondents were significantly different (p = 0.0117). In addition, the agreement among the generative AI models was significant (intraclass correlation coefficient [ICC] = 0.628), but there was no agreement between the residents (Kappa = –0.376). The explanation of generative AI models in support of answer was 44.72% accurate. Conclusion Humans exhibited superior accuracy compared to the AI models, showcasing a stronger comprehension of the subject matter. All three AI models included in the study could not achieve the minimum percentage needed to pass an FRCR2A examination. However, generative AI models showed significant agreement in their answers where the residents exhibited low agreement, highlighting a lack of consistency in their responses.

28 December 2023 in Indian Journal of Radiology and Imaging
Verified
Journal Article
Open access
PDF file
PSPradosh Kumar Sarangi
Pradosh Kumar Sarangi
AIAparna Irodi
Aparna Irodi
SPSwaha Panda
Swaha Panda
DNDEBASISH SWAPNESH KUMAR NAYAK
DEBASISH SWAPNESH KUMAR NAYAK
Himel MondalHimel Mondal
Himel Mondal
Background Differential diagnosis in radiology is a critical aspect of clinical decision-making. Radiologists in the early stages may find difficulties in listing the differential diagnosis from image patterns. In this context, the emergence of large language models (LLMs) has introduced new opportunities as these models have the capacity to access and contextualize extensive information from text-based input. Objective The objective of this study was to explore the utility of four LLMs—ChatGPT3.5, Google Bard, Microsoft Bing, and Perplexity—in providing most important differential diagnoses of cardiovascular and thoracic imaging patterns. Methods We selected 15 unique cardiovascular (n = 5) and thoracic (n = 10) imaging patterns. We asked each model to generate top 5 most important differential diagnoses for every pattern. Concurrently, a panel of two cardiothoracic radiologists independently identified top 5 differentials for each case and came to consensus when discrepancies occurred. We checked the concordance and acceptance of LLM-generated differentials with the consensus differential diagnosis. Categorical variables were compared by binomial, chi-squared, or Fisher's exact test. Results A total of 15 cases with five differentials generated a total of 75 items to analyze. The highest level of concordance was observed for diagnoses provided by Perplexity (66.67%), followed by ChatGPT (65.33%) and Bing (62.67%). The lowest score was for Bard with 45.33% of concordance with expert consensus. The acceptance rate was highest for Perplexity (90.67%), followed by Bing (89.33%) and ChatGPT (85.33%). The lowest acceptance rate was for Bard (69.33%). Conclusion Four LLMs—ChatGPT3.5, Google Bard, Microsoft Bing, and Perplexity—generated differential diagnoses had high level of acceptance but relatively lower concordance. There were significant differences in acceptance and concordance among the LLMs. Hence, it is important to carefully select the suitable model for usage in patient care or in medical education.

4 July 2024 in Indian Journal of Radiology and Imaging
Verified
Journal Article
Open access
PDF file
PSPradosh Kumar Sarangi
Pradosh Kumar Sarangi
SDSuvrankar Datta
Suvrankar Datta
MSM. Sarthak Swarup
M. Sarthak Swarup
SPSwaha Panda
Swaha Panda
DNDEBASISH SWAPNESH KUMAR NAYAK
DEBASISH SWAPNESH KUMAR NAYAK
Himel MondalHimel Mondal
Himel Mondal
Background Artificial intelligence chatbots have demonstrated potential to enhance clinical decision-making and streamline health care workflows, potentially alleviating administrative burdens. However, the contribution of AI chatbots to radiologic decision-making for clinical scenarios remains insufficiently explored. This study evaluates the accuracy and reliability of four prominent Large Language Models (LLMs)—Microsoft Bing, Claude, ChatGPT 3.5, and Perplexity—in offering clinical decision support for initial imaging for suspected pulmonary embolism (PE). Methods Open-ended (OE) and select-all-that-apply (SATA) questions were crafted, covering four variants of case scenarios of PE in-line with the American College of Radiology Appropriateness Criteria. These questions were presented to the LLMs by three radiologists from diverse geographical regions and setups. The responses were evaluated based on established scoring criteria, with a maximum achievable score of 2 points for OE responses and 1 point for each correct answer in SATA questions. To enable comparative analysis, scores were normalized (score divided by the maximum achievable score). Result In OE questions, Perplexity achieved the highest accuracy (0.83), while Claude had the lowest (0.58), with Bing and ChatGPT each scoring 0.75. For SATA questions, Bing led with an accuracy of 0.96, Perplexity was the lowest at 0.56, and both Claude and ChatGPT scored 0.6. Overall, OE questions saw higher scores (0.73) compared to SATA (0.68). There is poor agreement among radiologists' scores for OE (Intraclass Correlation Coefficient [ICC] = −0.067, p = 0.54), while there is strong agreement for SATA (ICC = 0.875, p < 0.001). Conclusion The study revealed variations in accuracy across LLMs for both OE and SATA questions. Perplexity showed superior performance in OE questions, while Bing excelled in SATA questions. OE queries yielded better overall results. The current inconsistencies in LLM accuracy highlight the importance of further refinement before these tools can be reliably integrated into clinical practice, with a need for additional LLM fine-tuning and judicious selection by radiologists to achieve consistent and reliable support for decision-making.

30 September 2024 in Cureus
Verified
Journal Article
Open access
PDF file
ABArijita Banerjee
Arijita Banerjee
PSPradosh Kumar Sarangi
Pradosh Kumar Sarangi
SKSumit Kumar
Sumit Kumar
Introduction With the current exponential expansion of robotics, implants, and imaging technologies, diagnostic processes within the healthcare industry are becoming popular platforms for artificial intelligence (AI) use. Thus, an understanding of physicians’ attitudes toward AI and the extent to which medical educators are ready to work with AI is necessary. This research aimed to study doctors’ perceptions of AI in healthcare. Methods A web-based questionnaire organized into four sections, namely, demographics, concepts of AI, education in AI, and implementation challenges related to AI, was designed systematically based on a literature search and circulated among medical doctors from various fields. Results Study participants exhibited a lower score toward familiarity with AI. Only 52.12% (74/142) of physicians completed the survey. The greatest challenge associated with the use of AI in therapeutic settings was found to be the degree of autonomy, with a score of 3.56. Among the participants, 67.61% felt that the lack of human supervision was the most important limiting factor in the implementation of AI in clinical practice. However, the participants demonstrated a strong interest in understanding the concepts of AI in the near future. Conclusion This study revealed a low degree of familiarity with AI, highlighting the need for medical schools and hospitals to establish specialized education and training programs for physicians to improve patient outcomes.

4 November 2024 in Indian Journal of Radiology and Imaging
Verified
Journal Article
Open access
PDF file
PSPradosh Kumar Sarangi
Pradosh Kumar Sarangi
SDSuvrankar Datta
Suvrankar Datta
BPBraja Behari Panda
Braja Behari Panda
SPSwaha Panda
Swaha Panda
Himel MondalHimel Mondal
Himel Mondal
Background Radiology is critical for diagnosis and patient care, relying heavily on accurate image interpretation. Recent advancements in artificial intelligence (AI) and natural language processing (NLP) have raised interest in the potential of AI models to support radiologists, although robust research on AI performance in this field is still emerging. Objective This study aimed to assess the efficacy of ChatGPT-4 in answering radiological anatomy questions similar to those in the Fellowship of the Royal College of Radiologists (FRCR) Part 1 Anatomy examination. Materials and Methods We used 100 mock radiological anatomy questions from a free Web site patterned after the FRCR Part 1 Anatomy examination. ChatGPT-4 was tested under two conditions: with and without context regarding the examination instructions and question format. The main query posed was: “Identify the structure indicated by the arrow(s).” Responses were evaluated against correct answers, and two expert radiologists (>5 and 30 years of experience in radiology diagnostics and academics) rated the explanation of the answers. We calculated four scores: correctness, sidedness, modality identification, and approximation. The latter considers partial correctness if the identified structure is present but not the focus of the question. Results Both testing conditions saw ChatGPT-4 underperform, with correctness scores of 4 and 7.5% for no context and with context, respectively. However, it identified the imaging modality with 100% accuracy. The model scored over 50% on the approximation metric, where it identified present structures not indicated by the arrow. However, it struggled with identifying the correct side of the structure, scoring approximately 42 and 40% in the no context and with context settings, respectively. Only 32% of the responses were similar across the two settings. Conclusion Despite its ability to correctly recognize the imaging modality, ChatGPT-4 has significant limitations in interpreting normal radiological anatomy. This indicates the necessity for enhanced training in normal anatomy to better interpret abnormal radiological images. Identifying the correct side of structures in radiological images also remains a challenge for ChatGPT-4.

25 March 2024 in Indian Journal of Radiology and Imaging
Verified
Journal Article
Open access
PDF file
PSPradosh Kumar Sarangi
Pradosh Kumar Sarangi
Himel MondalHimel Mondal
Himel Mondal
Assessing the Capability of ChatGPT, Google Bard, and Microsoft Bing in Solving Radiology Case Vignette We appreciate the opportunity to respond to the letter written in response to our published article titled “Assessing the capability of ChatGPT, Google Bard, and Microsoft Bing in solving radiology case vignettes.”[1] We thank the authors for their interest in our work and thoughtful questions. The use of large language models (LLMs) like ChatGPT, Google Bard, Microsoft Bing, etc., in radiology is indeed a burgeoning field, and we are pleased that our study has sparked further discussion. We would like to address the raised concerns and provide additional information to enhance the clarity of our methodology. The authors asked us about the input prompts. We used the Fellowship of the Royal College of Radiologists Part 2A pattern questions directly as prompts. There was no prefix (e.g., role definition) or suffix (e.g., customizing response for reader) attached to the prompt. [Fig. 1] present such a question used as a prompt in ChatGPT (GPT3.5; free version). We appreciate the authors' acknowledgment of the potential influence of prompt engineering on the performance of LLMs. Indeed, the intricacies of prompt design can change the response drastically. We summarized top ten tips in [Table 1] about designing prompts for better output from the LLM. There are several websites that help training prompt engineering.[2] [3] The authors raise a valid question about any training we used for the chatbots. We confirm that the chatbots, including ChatGPT, Google Bard, and Microsoft Bing, were not trained by us. Instead, we utilized pretrained models from the respective platforms to ensure a fair evaluation of their out-of-the-box diagnostic capabilities. However, studies have reported that fine-tuned GPT 3.5 and GPT 4 models have shown better responses.[4] We hope that these clarifications address the concerns raised by the authors. Thank you for providing this platform for academic discourse. Article published online: 25 March 2024 © 2024. Indian Radiological Association. This is an open access article published by Thieme under the terms of the Creative Commons Attribution-NonDerivative-NonCommercial License, permitting copying and reproduction so long as the original work is given appropriate credit. Contents may not be used for commercial purposes, or adapted, remixed, transformed or built upon. (https://creativecommons.org/licenses/by-nc-nd/4.0/) Thieme Medical and Scientific Publishers Pvt. Ltd. A-12, 2nd Floor, Sector 2, Noida-201301 UP, India