Is the Future of Medicine Just a Prompt Away?

In Evaluating General-Purpose LLMs for Patient-Facing Use: Dermatology-Centered Systematic Review and Meta-Analysis (medRxiv, 2025), the data tells a fascinating story: large language models (LLMs) are improving in medical reasoning, empathy, and safety - but they’re not perfect, and trust takes time to earn. Which, come to think of it, sounds a lot like the long human history of hoping for miracle healers.

Long before stethoscopes, scalpels, and sterile gloves, our first “doctors” were magicians - or at least, that’s what everyone believed. Prehistoric healers waved bones, mumbled incantations, and applied sometimes questionable herbal pastes. Yet enough patients recovered to keep the legend alive.

Fast forward a few millennia and not much has changed… except the props. The bone rattle has been replaced by a diagnostic app. The “spirit-cleansing smoke” is now an MRI scan. And our new shamans? They’re called AI engineers.

Just like in the old days, we still crave the miracle cure, the instant fix, the all-knowing healer. Our dream is a tireless personal doctor who remembers every ache, every allergy, every bit of medical literature (plus the plot of every episode of Grey’s Anatomy).

When ChatGPT burst into the public spotlight in late 2022, some were fascinated and some were wary. Could a chatbot really diagnose a rash? Suggest a safe treatment? Explain it all in plain language?

Early studies, including those reviewed in the paper, painted a mixed picture. In 2022, the mood was skeptical. By 2023, optimism surged as newer models like GPT-4, Claude, and Gemini started showing measurable gains in accuracy, empathy, and communication. But by 2025, the mood had shifted again - not to cynicism, but toward a more critical view.

The truth is, AI in medicine is a lot like the magic of old: it works impressively well in certain contexts, but not always when or how you expect. LLMs are now better at interpreting images, offering solid medication safety advice, and even admitting when they don’t know - a kind of digital humility our ancestors probably wished their witch doctors had. But they still have limits. Even when an AI aces a medical board exam and offers great second opinions, patients using it alone don’t necessarily make better decisions.

That’s why the paper calls for evaluator-aware, patient-in-the-loop frameworks - ways of measuring not just whether the AI gets the right answer, but whether it helps real people make better choices. Because in healthcare, as in magic, the spell only works if it actually helps the patient in the real world.

REFERENCE

Irene S. Gabashvili Evaluating General-Purpose LLMs for Patient-Facing Use: Dermatology-Centered Systematic Review and Meta-Analysis medRxiv 2025.08.11.25333149; doi: https://doi.org/10.1101/2025.08.11.25333149

Transforming Dermatology

Artificial intelligence has witnessed a rapid surge in the adoption of language models, with transformer-based pretrained language models (T-PLMs) playing a prominent role. These T-PLMs, such as BioBERT, MEP & Bioformer (BERT), Chatdoctor (LLaMA), OPAL & MedDialogue (BART), BioGPT and MedGPT (GPT 2), have revolutionized natural language processing in the biomedical research community, offering tailored performance for specific applications. Among these models, ChatGPT stands out due to its versatility, flexibility, and accessibility, making it widely applicable across various domains, including dermatology.

The fact that ChatGPT may be used by everyone, as opposed to models that can only be used by specialized developers and researchers, is one of its main advantages. This accessibility has paved the way for new possibilities in the field. By integrating clinical knowledge with interactive conversation, new generation of language models has the potential to transform all biomedical fields.

A recently posted preprint, open to peer review till July 8, focuses on the utilization of ChatGPT in dermatology. However, the study's conclusions have implications beyond dermatology and are relevant to other biomedical disciplines as well. Unlike previous reviews, this study goes further than performance evaluation by analyzing the actual utilization and real-world applications of ChatGPT in dermatology-related areas. By examining its practical use, the study offers valuable insights into the potential impact of ChatGPT in the broader biomedical research community. 

REFERENCE: 

Gabashvili IS. ChatGPT in Dermatology: A Comprehensive Systematic Review JMIR Preprints. 02/06/2023:48979. medRxiv 2023.06.11.23291252; https://doi.org/10.1101/2023.06.11.23291252 

Accelerating Knowledge Innovation: Systematic Review of Reviews on ChatGPT

In the beginning was the Word. It was used in the creation of all other things - from thoughts to stories and histories. However, as the amount of information available grew overwhelming, it became challenging to process and make sense of it all. Early academic reformers introduced the idea of reviews and digests to help navigate this sea of information. But it wasn't until the 1970s that systematic reviews gained popularity, starting in the field of medical research.

created by Author with ChatGPT, Bing Image Creator & Photoshop

Reviews play a crucial role in consolidating a vast array of studies and publications, allowing researchers to weave together the threads of evidence and create a cohesive and informative narrative. However, traditional review processes often require substantial time and the collaboration of multiple researchers to reach a consensus. With the rise of generative AI based on large language models, the power of words can be harnessed to streamline the systematic review process, unlocking new possibilities for learning and knowledge acquisition. By leveraging the capabilities of ChatGPT, researchers can potentially accelerate the production of high-quality reviews, facilitating the dissemination of insights and advancements in various fields of study.

The use of ChatGPT in conducting a systematic review of reviews on ChatGPT itself demonstrates the potential for accelerating the production of high-quality reviews in a timely manner. 

While systematic reviews are considered to be the gold standard in knowledge synthesis, they usually require between 6 months and 2 years to complete and often have a narrow focus. While the methodological shortcuts allow rapid reviews (first mentioned in the literature in 1997) to be conducted in less time and with fewer resources, they also increase the likelihood of introducing bias into the review process and missing important information from grey literature (i.e., preprint servers). 

In 2020, full systematic review was completed by a team of 6 in 2 weeks using automation tools. The most time-consuming tasks were data extraction, write-up, abstract screening, full-text screening, and risk of bias. 4 out of the 6 people on the team were experienced systematic reviewers with complementary skills (three experts in two domains required for the review and one information specialist). 

In 2023, ChatGPT and I were able to complete the review of reviews in one week. We screened 7 large resources of papers, including grey literature and reviewed primary studies in Chinese, German, Indonesian, Norwegian, Portuguese, Russian, and Spanish, in addition to English. 

ChatGPT helped me to filter relevant literature in all languages, extract key information, summarize findings, and even assisted with the synthesis of the overall review, enabling a more efficient and comprehensive analysis.

Our paper illustrates that ChatGPT is expanding into different domains and highlights the need to continually refine and expand the training datasets, ensuring that they are diverse and accurate. Another area of improvement involves developing customized integrations, designing specialized prompt instructions and involvement of domain-specific expert trainers, factual correctness evaluation, and investigation of societal impact.  

Word by word, paper by paper, and review by review, ChatGPT is paving the way for a future where knowledge creation is accelerated, insights are amplified, and breakthroughs are within closer reach.

REFERENCE

Gabashvili I.S. The impact and applications of ChatGPT: a systematic review of literature reviews. Submitted on May 8, 2023. arXiv:2305.18086 [cs.CY]. https://doi.org/10.48550/arXiv.2305.18086

Resolving the subtypes of COVID-19 in the elderly

SARS-Cov-2 is one of the most complex viruses known to medical science. Patients with COVID-19 present a broad spectrum of clinical manifestations, ranging from asymptomatic infection to lethal outcome. Both the young and the old may have very different clusters of symptoms and responses to medications, including the COVID-19 vaccines.  Each type is associated with how severe of an illness a patient might experience, ranging from asymptomatic to lethal. 

Precision medicine approaches such as whole-exome sequencing can provide insight into the phenotypes, endotypes and underlying mechanisms of the disease. The high cost of cutting-edge approaches, however, keeps these tools out of reach for many research teams. 

In this age of big data and large clinical studies, we should not forget about the value of individual cases. A good case report tells a detailed story. It describes a unique phenotype and offers unique clues to its resolution into an endotype. 

A new systematic review of case reports aims to answer questions about COVID-19 subtypes in octogenarians, nonagenarians, and centenarians and offer possible solutions to organize the knowledge and identify the gaps. 

REFERENCE

Irene S. Gabashvili. The outcomes of COVID-19 vaccination and SARS-CoV-2 infection in octogenarians, nonagenarians, and centenarians. PROSPERO 2022 CRD42022332621 Available from: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022332621

Irene S. Gabashvili (2022), “COVID-19 vaccine and SARS-CoV-2 in the oldest old: rapid literature review”, Mendeley Data, v1 http://dx.doi.org/10.17632/6sk33d9z7s.1 https://data.mendeley.com/datasets/6sk33d9z7s/1

Irene S. Gabashvili (2022), “The Outcomes of COVID-19 and Vaccination in the Oldest Old: a Longitudinal Observational Study and Literature Review”, April 2022, DOI: 10.13140/RG.2.2.15625.93285