Expertise in AI and clinical publishing exposes peer review gaps: A perspective

Abstract

Artificial intelligence and machine learning are advancing rapidly in medical and mental health research, yet clinical publishing remains structurally unprepared to evaluate these technologies with the rigor they demand. Despite the rise of AI-driven models for suicide risk prediction and diagnostic assessment, editorial and peer review processes often lack the technical expertise required to assess methodological validity. Drawing on dual fluency in AI and clinical publishing, this perspective identifies a critical gap at the intersection of innovation and editorial oversight. This article reveals how editorial decisions in high-impact psychiatry journals have dismissed valid methodological concerns as “overly technical” and undermined independent scientific critique, drawing on two case studies: one involving a model that differentiates suicidal from non-suicidal self-harm, and another analyzing speech-based suicide risk assessment. These case studies serve as the foundation for a broader critique of editorial decision-making in clinical publishing, revealing persistent structural blind spots in evaluating AI-integrated research. To prevent the pre-mature adoption of flawed models in clinical care, this perspective proposes targeted reforms: recruiting technically proficient reviewers, mandating transparent methodological reporting, and protecting space for independent post-publication evaluation. Without such changes, the integrity of the field and the safety of patients remain at risk.

Keywords

Artificial intelligence / Peer review-research / Ethics-research / Editorial policies / Speech analysis

Funding

None.

Conflict of interest

The author has previously submitted critiques to the Journal of Affective Disorders regarding AI methodologies in clinical research, which were not accepted for publication. While this perspective discusses editorial practices in AI research - including Journal of Affective Disorders - the analysis is conducted independently, without financial or institutional influence. The views expressed reflect methodological and ethical concerns relevant to AI-driven mental health research and do not stem from any personal, professional, or financial stake in the journal or related entities.

References

[1] Umar BU, Ajao LA, Dogo EM, Ajao FJ, Atama M. Artificial intelligence model for prediction of cardiovascular disease: An empirical study. Artif Intell Health. 2023; 1(1):42-56. doi: 10.36922/aih.1746

[2] Nawab K. Artificial intelligence scribe: A new era in medical documentation. Artif Intell Health. 2024; 1(4):12-15. doi: 10.36922/aih.3103

[3] Kong Y, Guerrero E, Frimpong J, et al. A machine learning approach to unravel client and program-specific effects in opioid treatment retention. Artif Intell Health. 2024; 2(1):105-113. doi: 10.36922/aih.3750

[4] Wicklem LC, San Hwang S, Lau BT, Bhave M, Chee XW. Machine learning-driven prediction of EBNA1 inhibitors against Epstein-Barr virus in nasopharyngeal carcinoma. Artif Intell Health. 2024; 2(1):93-104. doi: 10.36922/aih.4375

[5] Gogineni AK, Hitesh M, Jha PK, Sen SS, Das S, Sahu KK. Deep learning on chest X-ray and computed tomography scans for detection of COVID-19 as a part of a network-centric digital health stack for future pandemics. Artif Intell Health. 2024; 2(1):29-41. doi: 10.36922/aih.2888

[6] Casiraghi JL, Lizio A, Bolognini S, et al. Exploring the viability of robotic technology integrated with Vivaldi artificial intelligence for functional assessment in amyotrophic lateral sclerosis. Artif Intell Health. 2024; 1(4):73-84. doi: 10.36922/aih.3732

[7] Schwingel PA, Schwingel D, De Aquino SR, et al. An exploratory study on the potential of ChatGPT as an AI-assisted diagnostic tool for visceral leishmaniasis. Artif Intell Health. 2024; 1(4):97-106. doi: 10.36922/aih.3930

[8] Luu MSK, Tuchinov BN, Prokaeva AI, Korobko DS, Malkova NA, Tulupov AA. Discovering predictive features of multiple sclerosis from clinically isolated syndrome with machine learning. Artif Intell Health. 2024; 1(4):107-122. doi: 10.36922/aih.4255

[9] Thomas C, Prasad RR. Health-care app detection using optimized clustering. Artif Intell Health. 2024; 1(4):16-29. doi: 10.36922/aih.2585

[10] Vishwanath AB, Srinivasalu VK, Subramaniam N. Role of large language models in improving provider-patient experience and interaction efficiency: A scoping review. Artif Intell Health. 2024; 2(2):1-10. doi: 10.36922/aih.4808

[11] Haghish EF. Differentiating adolescent suicidal and nonsuicidal self-harm with artificial intelligence: Beyond suicidal intent and capability for suicide. J Affecti Disord. 2025; 378:381-391. doi: 10.1016/j.jad.2025.02.015

[12] Ding Z, Zhou Y, Dai AJ, et al. Speech based suicide risk recognition for crisis intervention hotlines using explainable multi-task learning. J Affect Disord. 2025; 370:392-400. doi: 10.1016/j.jad.2024.11.022

[13] Gulumbe BH. Obvious artificial intelligence-generated anomalies in published journal articles: A call for enhanced editorial diligence. Learn Publ. 2024; 37(4):1-5. doi: 10.1002/leap.1626

[14] Leveridge M. This editorial about AI in publishing was definitely written by a human. Can Urol Assoc J. 2023; 17(6):151-152. doi: 10.5489/cuaj.8424

[15] Tonmoy STI. Embeddings at BLP- 2023 Task 2:Optimizing fine-tuned transformers with cost-sensitive learning for multiclass sentiment analysis. In: Proceedings of the First Workshop on Bangla Language Processing. 2023. p. 340-346.

[16] Qi X, Wang S, Fang C, Jia J, Lin L, Yuan T. Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants. Redox Biol. 2025; 79:103470. doi: 10.1016/j.redox.2024.103470

[17] Ahmed U, Jiangbin Z, Almogren A, et al. Hybrid bagging and boosting with SHAP based feature selection for enhanced predictive modeling in intrusion detection systems. Sci Rep. 2024; 14:30532. doi: 10.1038/s41598-024-81151-1

[18] Alkhawaldeh IM, Albalkhi I, Naswhan AJ. Challenges and limitations of synthetic minority oversampling techniques in machine learning. World J Methodol. 2023; 13(5):373-378. doi: 10.5662/wjm.v13.i5.373

[19] Ganjavi C, Eppler MB, Pekcan A, et al. Publishers’ and journals’ instructions to authors on use of generative artificial intelligence in academic and scientific publishing: Bibliometric analysis. BMJ. doi: 10.1136/bmj-2023-077192

[20] Jackson P, Weaver CC, editors. Rethinking Peer Review: Critical Reflections on a Pedagogical Practice. Colorado: WAC Clearinghouse; 2023.

[21] Smith R. Peer review: A flawed process at the heart of science and journals. J R Soc Med. 2006; 99(4):178-182. doi: 10.1177/014107680609900414

[22] Joloudari JH, Marefat A, Nematollahi MA, Oyelere SS, Hussain S. Effective class-imbalance learning based on SMOTE and convolutional neural networks. Appl Sci. 2023; 13(6):4006. doi: 10.3390/app13064006

[23] Araf I, Idri A, Chairi I. Cost-sensitive learning for imbalanced medical data: A review. Artif Intell Rev. 2024; 57:80. doi: 10.1007/s10462-023-10652-8

[24] Baevski A, Zhou F, Mohamed AR. Wav2Vec 2.0:A framework for self-supervised learning of speech representations. In: Proceedings of NeurlIPS. 2020.

[25] Daneshfar F, Kabudian SJ. Speech emotion recognition using discriminative dimension reduction by employing a modified quantum-behaved particle swarm optimization algorithm. Multimed Tools Appl. 2020; 79(1):1261-1289. doi: 10.1007/s11042-019-08222-8

[26] Das R, Singh TD. Multimodal sentiment analysis: A survey of methods, trends, and challenges. ACM Comput Surv. 2023; 55(13s):1-38. doi: 10.1145/3586075

[27] Pfeifer E, Wittmann M. Waiting, thinking, and feeling: Variations in the perception of time during silence. Front Psychol. 2020; 11:602. doi: 10.3389/fpsyg.2020.00602

[28] Sharrab YO, Attar H, Eljinini MAH, Al-Omary Y, Al-Momani W. Advancements in speech recognition: A systematic review of deep learning transformer models, trends, innovations, and future directions. IEEE Access. 2025; 13:46925. doi: 10.1109/ACCESS.2025.3550855

[29] Vinciarelli A, Pantic M, Bourlard H. Social signal processing: Survey of an emerging domain. Image Vision Comput. 2009; 27(12):1743-1759. doi: 10.1016/j.imavis.2008.11.007

[30] Choi J, Liu Z, Xu P. Advancing artificial intelligence in mental health: Ethical considerations in machine learning applications. J Affect Disord. 2024; 379:302-314. doi: 10.1016/j.jad.2024.03.017

[31] Gong Y. Navigating the future of clinical informatics: A focus on patient safety, AI integration, and education. J Clin Inform. 2024; 1(1):4988. doi: 10.36922/jci.4988

[32] Merriman B. Peer review as an evolving response to organizational constraint: Evidence from sociology journals, 1952-2018. Am Soc. 2021; 52(3):341-366. doi: 10.1007/s12108-020-09473-x

[33] Murray D, Siler K, Larivière V, et al. Gender and International Diversity Improves Equity in Peer Review. bioRxiv [Preprint]; 2018. doi: 10.1101/400515

[34] Lerback JC, Hanson B, Wooden P. Association between author diversity and acceptance rates and citations in peer-reviewed Earth science manuscripts. Earth Space Sci. 2020; 7(5):e2019EA000946. doi: 10.1029/2019EA000946

[35] Callaham M. Gender bias and peer review: Annals seeks greater diversity. Ann Emerg Med. 2019; 74(6):736-739. doi: 10.1016/j.annemergmed.2019.08.432

[36] Drozdz JA, Ladomery MR. The peer review process: Past, present, and future. Br J Biomed Sci. 2024; 81:12054. doi: 10.3389/bjbs.2024.12054

[37] Khalifa AA. A letter to the editor: The peer review process: Past, present, and future. Br J Biomed Sci. 2025; 81:14125. doi: 10.3389/bjbs.2024.14125

[38] Siau K, El-Omar E. How to write a letter to the editor. United European Gastroenterol J. 2020; 8(8):981-983. doi: 10.1177/2050640620956921

[39] Rieke N, Hancox J, Li W, et al. The future of digital health with federated learning. NPJ Digit Med. 2020; 3(1):119. doi: 10.1038/s41746-020-00323-1

[40] Gallifant J, Fiske A, Levites Strekalova YA, et al. Peer review of GPT-4 technical report and systems card. PLOS Digit Health. 2024; 3(1):e0000417. doi: 10.1371/journal.pdig.0000417

[41] McLennan S, Fiske A, Tigard D, Müller R, Haddadin S, Buyx A. Embedded ethics: A proposal for integrating ethics into the development of medical AI. BMC Med Ethics. 2022; 23(1):6. doi: 10.1186/s12910-022-00746-3

[42] McLennan S, Fiske A, Celi LA, et al. An embedded ethics approach for AI development. Nat Mach Intell. 2020; 2(9):488-490. doi: 10.1038/s42256-020-0214-1

[43] Fiske A, Prainsack B, Buyx A. Data work: Meaning-making in the era of data-rich medicine. J Med Internet Res. 2019; 21(7):e11672. doi: 10.2196/11672

[44] Fiske A, Buyx A, Prainsack B. Health information counselors: A new profession for the age of big data. Acad Med. 2019; 94(1):37-41. doi: 10.1097/ACM.0000000000002395

[45] McLennan S, Lee MM, Fiske A, Celi LA. AI ethics is not a panacea. Am J Bioeth. 2020; 20(11):20-2. doi: 10.1080/15265161.2020.1819470

[46] Ali Z, Yang MS. Analysis of renewable energies based on circular bipolar complex intuitionistic fuzzy linguistic information with Frank power aggregation operators and MABAC model. Int J Comput Intell Syst. 2025; 18(1):1-40. doi: 10.1007/s44196-025-00800-z

[47] Tanveer M, Sajid M, Akhtar M, et al. Fuzzy deep learning for the diagnosis of Alzheimer’s disease: Approaches and challenges. IEEE Trans Fuzzy Syst. 2024; 32(10):5477-5492. doi: 10.1109/TFUZZ.2024.3409412

[48] Apostolopoulos ID, Papandrianos NI, Papathanasiou ND, Papageorgiou EI. Fuzzy cognitive map applications in medicine over the last two decades: A review study. Bioengineering (Basel). 2024; 11(2):139. doi: 10.3390/bioengineering11020139

[49] Rafieisangari R, Shiri N. A multi-adaptive neuro-fuzzy inference system with variable thresholds for heartbeat classification. Artif Intell Health. 2024; 1(4):43-60. doi: 10.36922/aih.3367

[50] Alrasheedi AF, Mishra AR, Alshamrani AM, Rani P, Pamucar D. Decision-analytics-based risk allocation in the micromobility sector: Sugeno-Weber operators and picture fuzzy distance methodology. Cognit Comput. 2024; 16(6):3122-3148. doi: 10.1007/s12559-024-10333-w

[51] Mandelbrot BB, Evertsz CJ, Gutzwiller MC. Fractals and Chaos: The Mandelbrot Set and Beyond. Vol. 3. Berlin: Springer; 2004.

[52] Devaney R. An Introduction to Chaotic Dynamical Systems. United States: CRC Press; 2018.

[53] Devaney RL. A First Course in Chaotic Dynamical Systems: Theory and Experiment. United States: CRC Press; 2018.

[54] Flake GW. The Computational Beauty of Nature: Computer Explorations of Fractals, Chaos, Complex Systems, and Adaptation. United States: MIT Press; 2000.

[55] Barnsley MF. Fractals Everywhere. United States: Academic Press; 2014.

[56] Schroeder M. Fractals, Chaos, Power Laws: Minutes from an Infinite Paradise. United States: Courier Corporation; 2009.

[57] Falconer K. Fractal Geometry: Mathematical Foundations and Applications. United States: John Wiley and Sons; 2013.