AI bias in lung cancer radiotherapy

Abstract

Aim: In lung cancer research, AI has been trained to read chest radiographs, which has led to improved health outcomes. However, the use of AI in healthcare settings is not without its own set of drawbacks, with bias being primary among them. This study seeks to investigate AI bias in diagnosing and treating lung cancer patients. The research objectives of this study are threefold: 1) To determine which features of patient datasets are most susceptible to AI bias; 2) to then measure the extent of such bias; and 3) from the findings generated, offer recommendations for overcoming the pitfalls of AI in lung cancer therapy for the delivery of more accurate and equitable healthcare.

Methods: We created a synthetic database consisting of 50 lung cancer patients using a large language model (LLM). We then used a logistic regression model to detect bias in AI-informed treatment plans.

Results: The empirical results from our synthetic patient data illustrate AI bias along the lines of (1) patient demographics (specifically, age) and (2) disease classification/histology. As it concerns patient age, the model exhibited an accuracy rate of 82.7% for patients < 60 years compared to 85.7% for patients ≥ 60 years. Regarding disease type, the model was less adept in identifying treatment categories for adenocarcinoma (accuracy rate: 83.7%) than it was in predicting treatment categories for squamous cell carcinoma (accuracy rate: 92.3%).

Conclusions: We address the implications of such results in terms of how they may exacerbate existing health disparities for certain patient populations. We conclude by outlining several strategies for addressing AI bias, including generating a more robust training dataset, developing software tools to detect bias, making the model’s code open access and soliciting user feedback, inviting oversight from an ethics review board, and augmenting patient datasets by synthesizing the underrepresented data.

Keywords

AI / bias / lung cancer / large language models / health disparities

References

[1] Key Statistics for Lung Cancer [Internet].American Cancer Society, Inc.; c2024 [cited 2024 Sep 2]. Available from:https://www.cancer.org/cancer/types/lung-cancer/about/key-statistics.html#:~:text=Lung%20cancer%20(both%20small%20cell,(not%20counting%20skin%20cancer

[2] Lung cancer [Internet]. WHO; c2024 [cited 2024 Aug 31]. Available from:https://www.who.int/news-room/fact-sheets/detail/lung-cancer

[3] Small Cell Lung Cancer vs. Non-small Cell Lung Cancer: What’s the Difference? [Internet]. Rockville: National Foundation for Cancer Research; c2024 [cited2024 Aug 21]. Available from:https://www.nfcr.org/blog/small-cell-lung-cancer-vs-non-small-cell-lung-cancer-whats-the-difference/

[4] Lemjabbar-Alaoui H, Hassan OU, Yang YW, Buchanan P. Lung cancer: Biology and treatment options. Biochim Biophys Acta. 2015; 1856:189-210.

[5] Gomes RG, Vwalika B, Lee C, Willis A, Sieniek M, Price JT, et al. AI system for fetal ultrasound in low-resource settings. arXiv:2203.10139 [Preprint].2022 [cited 2024 Jul 15]. Available from:https://arxiv.org/abs/2203.10139

[6] Chan KS, Zary N. Applications and Challenges of Implementing Artificial Intelligence in Medical Education: Integrative Review. JMIR Med Educ. 2019; 5:e13930.

[7] Chi EA, Chi G, Tsui CT, Jiang Y, Jarr K, Kulkarni CV, et al. Development and Validation of an Artificial Intelligence System to Optimize Clinician Review of Patient Records. JAMA Netw Open. 2021; 4:e2117391.

[8] Svoboda E. Artificial intelligence is improving the detection of lung cancer. Nature. 2020; 587:S20-2.

[9] Huang S, Yang J, Shen N, Xu Q, Zhao Q. Artificial intelligence in lung cancer diagnosis and prognosis: Current application and future perspective. Semin Cancer Biol. 2023; 89:30-7.

[10] Ardila D, Kiraly AP, Bharadwaj S, Choi B, Reicher JJ, Peng L, et al. End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med. 2019; 25:954-61.

[11] AI Beats Radiologists for Accuracy in Lung Cancer Screening [Internet].WebMD LLC.; c2024 [cited 2024 Aug 11]. Available from:https://www.medscape.com/viewarticle/913428?form=fpf

[12] The Radiology Labor Shortage [Internet]. Reston: American College of Radiology; c2023 [cited 2024 Sep 3]. Available from:https://www.acr.org/Practice-Management-Quality-Informatics/ACR-Bulletin/Articles/March-2022/The-Radiology-Labor-Shortage

[13] Coccia M. Deep learning technology for improving cancer care in society: New directions in cancer imaging driven by artificial intelligence. Technol Soc. 2020; 60:101198.

[14] Coccia M. Converging Artificial Intelligence and Quantum Technologies: Accelerated Growth Effects in Technological Evolution. Technologies. 2024; 12:66.

[15] Yang Y, Jin G, Pang Y, Wang W, Zhang H, Tuo G, et al. The diagnostic accuracy of artificial intelligence in thoracic diseases: A protocol for systematic review and meta-analysis. Medicine (Baltimore). 2020; 99:e19114.

[16] Sourlos N, Wang J, Nagaraj Y, van Ooijen P, Vliegenthart R. Possible Bias in Supervised Deep Learning Algorithms for CT Lung Nodule Detection and Classification. Cancers (Basel). 2022; 14:3867.

[17] Tasci E, Zhuge Y, Camphausen K, Krauze AV. Bias and Class Imbalance in Oncologic Data-Towards Inclusive and Transferrable AI in Large Scale Oncology Data Sets. Cancers (Basel). 2022; 14:2897.

[18] Parikh RB, Teeple S, Navathe AS. Addressing Bias in Artificial Intelligence in Health Care. JAMA. 2019; 322:2377-8.

[19] Guo LN, Lee MS, Kassamali B, Mita C, Nambudiri VE. Bias in, bias out: Underreporting and underrepresentation of diverse skin types in machine learning research for skin cancer detection-A scoping review. J Am Acad Dermatol. 2022; 87:157-9.

[20] Voong KR, Hazell SZ, Fu W, Hu C, Lin CT, Ding K, et al. Relationship Between Prior Radiotherapy and Checkpoint-Inhibitor Pneumonitis in Patients With Advanced Non-Small-Cell Lung Cancer. Clin Lung Cancer. 2019; 20:e470-9.

[21] Larrazabal AJ, Nieto N, Peterson V, Milone DH, Ferrante E. Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis. Proc Natl Acad Sci U S A. 2020; 117:12592-4.

[22] Tsutani Y, Miyata Y, Nakayama H, Okumura S, Adachi S, Yoshimura M, et al. Solid tumor size on high-resolution computed tomography and maximum standardized uptake on positron emission tomography for new clinical T descriptors with T1 lung adenocarcinoma. Ann Oncol. 2013; 24:2376-81.

[23] Viswanathan VS, Toro P, Corredor G, Mukhopadhyay S, Madabhushi A. The state of the art for artificial intelligence in lung digital pathology. J Pathol. 2022; 257:413-29.

[24] Age and Cancer Risk [Internet]. National Cancer Institute; [cited 2024 Sep 23]. Available from:https://www.cancer.gov/about-cancer/causes-prevention/risk/age

[25] Social determinants of health [Internet]. WHO; c2024 [cited2024 Aug 15]. Available from:https://www.who.int/health-topics/social-determinants-of-health#tab=tab_1

[26] Lung cancer types [Internet].The Johns Hopkins University, The Johns Hopkins Hospital, and Johns Hopkins Health System; c2024 [cited 2024 Aug 18]. Available from:https://www.hopkinsmedicine.org/health/conditions-and-diseases/lung-cancer/lung-cancer-types#:~:text=What%20You%20Need%20to%20Know%201%20The%20most,size%2C%20recommended%20treatment%20options%20and%20rate%20of%20metastasis

[27] Carini C, Seyhan AA. Tribulations and future opportunities for artificial intelligence in precision medicine. J Transl Med. 2024; 22:411.

[28] He B, Sun C, Li H, Wang Y, She Y, Zhao M, et al. Breaking boundaries in radiology: redefining AI diagnostics via raw data ahead of reconstruction. Phys Med Biol. 2024; 69.

[29] Coccia M. Artificial intelligence technology in cancer imaging: Clinical challenges for detection of lung and breast cancer. J Soc Adm Sci. 2019; 6:82-98.