What Is the Role of AI in Psoriasis Assessment?

By Rasit Dinc

Psoriasis is a chronic, immune-mediated inflammatory disease that affects millions of people worldwide, causing a significant physical and psychological burden. [1] The assessment of psoriasis, which is crucial for determining the appropriate treatment and monitoring its effectiveness, has traditionally relied on subjective clinical evaluation. However, the advent of artificial intelligence (AI) is set to revolutionize this field, offering more objective, accurate, and efficient methods for psoriasis assessment.

Enhancing Diagnostic Accuracy

One of the most significant contributions of AI in dermatology is its ability to enhance diagnostic accuracy. Deep learning models, a subset of AI, can be trained on large datasets of skin images to recognize the subtle patterns of psoriasis and differentiate it from other skin conditions. For instance, a study by Zhao et al. demonstrated that a convolutional neural network (CNN) could diagnose common skin conditions, including psoriasis, with a misdiagnosis rate of only 3%, compared to 27% for dermatologists. [2] Furthermore, Google's AI-powered tool has shown performance non-inferior to that of board-certified dermatologists in identifying skin disorders, highlighting the potential of AI to support clinicians in making more accurate and timely diagnoses. [2]

Automating Severity Assessment

The Psoriasis Area and Severity Index (PASI) is the gold standard for assessing psoriasis severity, but its manual calculation is time-consuming and prone to inter-observer variability. AI-powered systems can automate this process, providing a more objective and reproducible assessment. Researchers like Huang et al. have developed deep learning models that can automatically calculate PASI scores from patient images with an accuracy comparable to that of dermatologists. [1, 2] Commercially available systems, such as FotoFinder ATBM® and VECTRA® WB360, are already incorporating AI to provide semi-automated or automated PASI calculations, streamlining the assessment process and reducing the workload of clinicians. [1]

Personalizing Treatment and Predicting Outcomes

Beyond diagnosis and severity assessment, AI is paving the way for personalized medicine in psoriasis treatment. By analyzing vast amounts of patient data, including clinical information, imaging data, and even genetic profiles, machine learning algorithms can predict how a patient is likely to respond to a particular treatment. For example, studies have shown that AI models can predict the efficacy of biologic therapies with high accuracy, helping clinicians select the most appropriate treatment for each patient from the outset. [2] This not only improves treatment outcomes but also avoids the trial-and-error approach that is often associated with psoriasis management. Furthermore, AI can help identify patients at a higher risk of developing comorbidities associated with psoriasis, such as psoriatic arthritis, enabling early intervention and preventative care. [2]

Challenges and the Road Ahead

Despite the immense potential of AI in psoriasis assessment, several challenges need to be addressed. These include the need for large, diverse, and well-annotated datasets to train and validate AI models, as well as the ethical and legal implications of using AI in clinical decision-making. Ensuring the generalizability of AI models across different populations and skin types is also crucial. However, with ongoing research and technological advancements, these challenges are likely to be overcome in the near future.

Conclusion

Artificial intelligence is poised to transform the landscape of psoriasis assessment. From enhancing diagnostic accuracy and automating severity scoring to personalizing treatment and predicting outcomes, AI offers a plethora of tools to improve the management of this chronic condition. As AI technologies continue to evolve and integrate into clinical practice, we can expect a new era of more precise, efficient, and patient-centered psoriasis care.

References

[1] Goessinger, E. V., Gottfrois, P., Mueller, A. M., Cerminara, S. E., & Navarini, A. A. (2024). Image-Based Artificial Intelligence in Psoriasis Assessment: The Beginning of a New Diagnostic Era?. American journal of clinical dermatology, 25(9), 861–872. https://doi.org/10.1007/s40257-024-00883-y [2] Barlow, R., & Young, H. (2024). AI in Psoriatic Disease: Scoping Review. JMIR Dermatology, 7, e50451. https://doi.org/10.2196/50451 [3] McMullen, E. P., Al Naser, Y. A., Maazi, M., Grewal, R. S., Abdel Hafeez, D., Folino, T. R., & Vender, R. B. (2025). Predicting psoriasis severity using machine learning: a systematic review. Clinical and Experimental Dermatology, 50(3), 520–528. https://doi.org/10.1093/ced/llae348 [4] Prithiviraj, A., Aarthi, M. A., & Venkateswaramurthy, N. (2025). Insights into the Impact of Artificial Intelligence on Psoriasis Treatment Strategies: A Mini Review. Indian Dermatology Online Journal, 16(6), 894–901. https://doi.org/10.4103/idoj.idoj_1055_24