Over the past decade, a plethora of software applications have emerged in the field of patient medical care, supporting the diagnosis and management of various clinical conditions^{14,15,20,21,22}. Our study contributes to this evolving field by introducing a novel application for holistic synkinesis diagnosis and leveraging the power of convolutional neural networks (CNN) to analyze images of periocular regions.

The development and validation of our CNN-based model for diagnosing facial synkinesis in FP patients mark a significant advancement in the realm of automated medical diagnostics. Our model demonstrated a high degree of accuracy (98.6%) in distinguishing between healthy individuals and those with synkinesis, with an F1-score of 98.4%, precision of 100%, and recall of 96.9%. These metrics highlight the model’s robustness and reliability, rendering it a valuable tool for clinicians. The confusion matrix analysis provided further insights into the model’s performance, revealing only one misclassification among the 71 test images. These metrics echo findings from previous work in diagnosing sequelae of FP. For example, our group reported comparable metrics for CNN-based assessment of lagophthalmos. Using a training set of 826 images, the validation accuracy was 97.8% over the span of 64 epochs¹⁷. Another study leveraged a CNN to automatically identify (peri-)ocular pathologies such as enophthalmos with an accuracy of 98.2%, underscoring the potential of neural networks when diagnosing facial conditions²³. Such tools can broaden access to FP diagnostics, thus reducing time-to-diagnosis and effectively triaging patients to the appropriate treatment pathway (e.g., conservative therapy, cross-face-nerve-grafts)^2,3,14,24. Overall, our CNN adds another highly accurate diagnostic tool for reliably detecting facial pathologies, especially in FP patients.

Another strength of our CNN lies in its high user-friendliness and rapid processing and training times. The mean image processing time was 24 ± 11 ms, and the overall training time was 14.4 min. The development of a lightweight, dockerized web application enhanced the model’s practicality and accessibility. In addition, the total development costs of the CNN were only $311 USD. Such parameters have been identified as key parameters for impactful AI research and effective integration into clinical workflows^25,26,27. More precisely, the short training times may pave the avenue toward additional AI-supported diagnostic tools in FP care to detect common short- and long-term complications of FP (e.g., ectropion, hemifacial tissue atrophy). The easy-to-use and cost-effective web application may facilitate clinical use for healthcare providers in low- and middle-income countries, where the incidence and prevalence of FP are higher compared to the high-income countries²⁸. To facilitate the download and use of our algorithm, we (i) uploaded the code to GitHub (San Francisco, USA), (ii) integrated the code into an application, and (iii) recorded an instructional video that details the different steps. Healthcare providers from low- and middle-income countries only require an internet connection to install the application. The instructional video will then guide them through the next steps to set up the application and start screening patients. Our application is free to use, and the number of daily screens is not limited. The rapid processing times also carry the potential to increase the screening throughput, further broadening the access to FP care and reducing waiting times for FP patients³. Collectively, the CNN represents a rapid, user-friendly, and cost-effective tool.

While our study presents promising results, it is not without limitations. The relatively small sample size, especially for the validation and test sets, suggests the need for further validation with larger and more diverse (i.e., multi-center, -racial, -surgeon) datasets to ensure the model’s robustness and generalizability. Additionally, the model’s ability to distinguish synkinesis from other facial conditions was not evaluated in this study, representing an area for future research. Moreover, integrating our model into clinical practice will require careful consideration of various factors, including user training, data privacy, and the ethical implications of automated diagnostics. Ensuring that clinicians are adequately trained to use the model and interpret its results is essential for maximizing its benefits. Additionally, robust data privacy measures must be implemented to protect sensitive patient information, particularly when using web-based applications. Thus, further validation is essential before clinical implementation. In a broader context, there are different AI/machine-learning-powered tools that have shown promising outcomes in pre-clinical studies and small patient samples (face transplantation, facial reanimation, etc.)^29,30,31,32. However, these tools remain to be investigated in larger-scale trials and integrated into standard clinical workup. Thus, cross-disciplinary efforts are needed to bridge the gap from bench to bedside and to fuel translational efforts.

By Leila Ugincius

Image-generative artificial intelligence makes ad creation faster and cheaper — but there’s an intriguing hook to the look, according to new research from Virginia Commonwealth University. Trust can plummet when AI-generated visuals depict service providers in industries where relationships matter.

So, how can AI help service marketers without compromising trust?

A study coauthored by César Zamudio, Ph.D., associate professor of marketing in the VCU School of Business, determined that selective AI use in ad creation is key.

“When tangible elements — like a doctor’s office environment — are AI-generated, but the service provider’s image is a real picture, trust and ad effectiveness are restored,” Zamudio said. “The takeaway? Use AI where it counts, and let the human element shine.”

This balance is crucial for small businesses as they market themselves. The smart move is to use AI to generate backgrounds, office settings or equipment — but keep real people in their ads. This way, businesses can still benefit from AI’s speed and cost savings without losing consumer confidence.

“Our research offers a simple, actionable strategy: Use AI for settings, not people,” Zamudio said. “This approach can help you cut ad costs without cutting credibility, giving you a real edge to beat bigger brands.”

The research is also relevant to consumers, who can use it to help navigate AI-driven marketing.

“Not all AI ads are misleading,” Zamudio said, “but knowing what’s real — and what’s not — can shape your trust in a brand. … Our study reveals how AI in advertising shapes trust, helping you stay informed, skeptical and aware in today’s digital marketing landscape.”

Smart AI use is key, he said. “Brands can harness AI’s efficiency without losing credibility by keeping real people front and center in service ads. Marketers can use this research to successfully walk the tightrope between innovation and consumer confidence.”

This is especially important for services, where ads help make intangible offerings feel real and trustworthy. With AI disclosures becoming more common due to government and industry pressures, businesses need to know how to design AI-driven ads that maintain consumer trust.

Zamudio’s study, “Service Ads in the Era of Generative AI: Disclosures, Trust and Intangibility,” was co-authored with colleagues from Missouri State University and Longwood University and was published recently in the Journal of Retailing and Consumer Services.