RCT demonstrates effectiveness of mylovia, a digital therapy for female sexual dysfunction

GAIA (Germany)

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

Sexual dysfunction is a reality for many women, but the subject remains taboo. A large percentage of women remain untreated, a problem that is exacerbated by the shortage of treatment options for female sexual dysfunction. A research team from GAIA in Hamburg, in cooperation with the Institute for Sexual, Psycho- and Trauma Therapy in Munich, the University of Lübeck, and the Medical School Hamburg, has now investigated the digital therapy “mylovia” The results of the randomized controlled trial (RCT) were published today in the peer-reviewed journal npj Digital Medicine and show a statistically significant and clinically relevant effect of mylovia.

mylovia supports women in overcoming sexual dysfunction to experience deeper pleasure and greater self-determination. The RCT enrolled 252 women aged 18 and above with a diagnosis of sexual dysfunction. After three months of using mylovia in addition to their usual treatment, a statistically significant and clinically relevant improvement in sexual function was observed in the intervention group compared to the control group (see graph). In addition, mylovia users reported significantly greater improvements in sexual desire, sexual satisfaction, and thoughts and behaviors related to sexual pain. The digital therapy shows similar effect sizes to face-to-face psychotherapy for female sexual dysfunction. As a self-guided intervention, mylovia can provide affected women with access to treatment, helping to close the gender health gap.

Wiebke Blaszcyk, sex therapist and study lead for mylovia at GAIA, explains: “We have a large problem in Germany regarding  treatment options for women with sexual dysfunction. Even gynecologists are often at a loss when it comes to libido, arousal, orgasm, and pain disorders once organic causes are ruled out. That's why we're particularly pleased that mylovia can effectively support these women.”

mylovia is a digital therapeutic using evidence-based psychological and psychotherapeutic methods. mylovia provides affected women with practical knowledge and specific exercises. Its main feature is a virtual dialogue that delivers information in brief and focused segments. Users engage with the program by choosing from a set of predefined responses the one that best aligns with their interests or individual situations. This triggers an empathetic exchange where the system acknowledges each input before offering the next piece of knowledge. The resulting process creates a continuous dynamic that mirrors the flow of an actual conversation.

Based on the positive study results, mylovia has been submitted to the German Federal Institute for Drugs and Medical Devices (BfArM) for reimbursement. If approved, the digital therapy would be prescribable by doctors and therapists as a Digital Health Application (DiGA), Germany’s prescription-based digital therapeutics program.

About GAIA  

GAIA is a global leader in the development of evidence-based, fully-automated and self-guided digital therapy systems that have benefited patients, physicians, and insurers for over two decades. Its product portfolio includes not only digital health applications (DiGA) but also numerous innovative therapeutics for mental health conditions, as well as other therapeutic areas such as immunology, rheumatology, MS, and back pain.

For over 25 years, GAIA has combined scientific, technological, and therapeutic expertise under one roof. Its goal is to support as many people as possible in restoring and maintaining their mental and physical health, thus improving their quality of life and well-being. The expert team at GAIA has confirmed the efficacy of its products in over 30 RCTs and meta-analyses. GAIA is the 48th member of the Association of Research-Based Pharmaceutical Companies (vfa). For more information, visit https://www.gaia-group.com.

 

---

Journal

npj Digital Medicine

DOI

10.1038/s41746-026-02385-z 

Method of Research

Randomized controlled/clinical trial

Subject of Research

People

Article Title

Digital intervention mylovia improves sexual functioning in women with sexual dysfunction in randomized controlled trial

Article Publication Date

3-Feb-2026

COI Statement

W.B., A.R., L.T.B., and G.A.J. are employed by GAIA, the developer and manufacturer of the intervention described in the study. J.P.K. received funding for clinical trials (German Federal Ministry of Health, Servier), payments for presentations on psychological internet interventions (GAIA, Oberberg, Servier, Stillachhaus), consulting fees from developers and distributors of psychological internet interventions (all about me, Boehringer, Ethypharm, GAIA, medac, sympatient) payments for workshops and books (Beltz, Elsevier, Hogrefe and Springer) on psychiatry, psychosomatics and psychotherapy. He is past president of the CBASP network (now DsG-CBASP) and serves as vice chairman of the chapters “Digital Psychiatry” and “Psychotherapy” of the German Psychiatric Association (DGPPN). J.S. and M.B. have no conflicts of interest to declare.

 

Wistar scientists demonstrate first-ever single-shot HIV vaccine neutralization success

The Wistar Institute

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

 

image: 

The Wistar Institute's Dr. Amelia Escolano

view more 

Credit: The Wistar Institute

PHILADELPHIA — (TUESDAY, FEB. 3, 2026) — Scientists at The Wistar Institute have developed an HIV vaccine candidate that achieves something never before observed in the field: inducing neutralizing antibodies against HIV after a single immunization in nonhuman primates. The innovative approach, published in Nature Immunology, could significantly shorten and simplify HIV vaccination protocols, making them more accessible worldwide.

The research, led by Amelia Escolano, Ph.D., assistant professor in Wistar’s Vaccine and Immunotherapy Center and the senior author of the study, centers on an engineered HIV envelope protein, WIN332, that challenges scientific assumptions about how to design an effective HIV vaccine.

“By going against one commonly held belief in the field, we achieved low neutralization after a single immunization, which was further increased after one additional booster, something that has never been observed before,” said Escolano. “Usually, HIV vaccination protocols require seven, eight, or even ten injections to start seeing any neutralization. For our immunogen, WIN332, we injected once and already saw some neutralization.”

For years, scientists attempting to engineer HIV vaccines have focused on targeting the virus’s envelope protein, a component of the outermost layer of the virus. Dr. Escolano’s team has engineered a specific region of the envelope protein, called the V3-glycan epitope. Conventional wisdom held that antibodies targeting this region required a particular sugar, N332-glycan, to bind effectively. All previous envelope immunogens were designed to preserve this sugar. Escolano’s team took the unprecedented step of removing the N332-glycan completely to create WIN332.

A single injection of WIN332 induced low but detectable neutralization against HIV within just three weeks—an unprecedented timeline. When the researchers gave a second injection using a related immunogen, neutralization levels increased significantly. This represents a potentially marked improvement over current experimental protocols.

“This immunogen could shorten and simplify vaccination protocols,” said Ignacio Relano-Rodriguez, Ph.D., first author of the study. “If this approach proves successful, we could potentially achieve desired immunity with just three injections. This would make vaccination protocols shorter and more affordable.”
By removing the N332-glycan to create their immunogen, the team also revealed the existence of two distinct types of HIV-neutralizing antibodies that target the V3-glycan region. Type I antibodies represent the previously known class that requires the N332 sugar to bind effectively. Type II antibodies are a new class, identified by this research, that doesn’t require the sugar for binding.

“This discovery potentially expands the toolkit available for developing HIV vaccines that provide broader protection against the diverse HIV strains circulating globally,” Escolano said.

The promising results have attracted attention from major global health organizations to advance WIN332 into human clinical trials. Meanwhile, additional preclinical evaluations are underway, along with the design of subsequent immunogens that could be used in a shortened vaccination series to further enhance neutralization efficiency.

Co-authors: Ignacio Relano-Rodriguez, Jianqiu Du, Zi Jie Lin, Margaret Kerwin, Marta Tarquis-Medina, Eduardo Urbano, Jiayan Cui, Rumi Habib, Colby Agostino, Sukanya Ghosh, Joyce Park, Caroline Boroughs, Niharika Shukla, David B. Weiner, Daniel W. Kulp, and Jesper Pallesen from The Wistar Institute; Meagan Watkins and Ronald S. Veazey from Tulane National Primate Research Center; Peng Zhao and Lance Wells from University of Georgia; Michael  S. Seaman from Beth Israel Deaconess Medical Center; Agnes A. Walsh, Mariane B. Melo, and Darrell J. Irvine from Scripps Research Institute; and George M. Shaw and Beatrice H. Hahn from University of Pennsylvania. 

Work supported by: National Institute of Allergy and Infectious Diseases (NIAID) grants R00 AI140770-03, P30 AI045008-23, P30 AI045008-24, and R01 AI172627-01A1 to A.E.; Gates Foundation INV-036995 to A.E.; 5 U19 AI166916-03 to J.P. U19 AI166916, BEAT-HIV UM1AI64570, and the a W.W. Smith Charitable Trust Distinguished Professorship in Cancer Research to D.B.W. National Institutes of Health grants R01GM130915 and R01AI157854 to L.W.; National Science Foundation Biofoundry: Glycoscience Research, Education, and Training Grant 2400220 to L.W.; and The Ching Jer Chern Postdoctoral Fellowship to I.R.R.

Publication information: Rapid Elicitation of Neutralizing Asn332-glycan-independent Antibodies to the V3-glycan epitope of HIV-1 Env in Nonhuman Primates, Nature Immunology, 2026. Online publication.
 
###

The Wistar Institute is an international leader in biomedical research with special expertise in cancer research and vaccine development. Founded in 1892 as the first independent nonprofit biomedical research institute in the United States, Wistar has held the prestigious Cancer Center designation from the National Cancer Institute since 1972. The Institute works actively to ensure that research advances move from the laboratory to the clinic as quickly as possible. wistar.org.
 

---

Journal

Nature Immunology

DOI

10.1038/s41590-025-02408-z 

Method of Research

Experimental study

Subject of Research

Animals

Article Title

Rapid elicitation of neutralizing Asn332-glycan-independent antibodies to the V3-glycan epitope of HIV-1 Env in nonhuman primates'

Article Publication Date

3-Feb-2026

 

Medical AI models need more context to prepare for the clinic

Marinka Zitnik outlines the challenges — and potential solutions

Harvard Medical School

FacebookXLinkedInWeChatBlueskyMessageWhatsAppEmail

Medical artificial intelligence is a hugely appealing concept. In theory, models can analyze vast amounts of information, recognize subtle patterns in data, and are never too tired or busy to provide a response. However, although thousands of these models have been and continue to be developed in academia and industry, very few of them have successfully transitioned into real-world clinical settings.

Marinka Zitnik, associate professor of biomedical informatics in the Blavatnik Institute at Harvard Medical School, and colleagues are exploring why — and how to close the gap between how well medical AI models perform on standardized test cases and how many issues the same models run into when they’re deployed in places like hospitals and doctors’ offices.

In a paper published Feb. 3 in Nature Medicine, the researchers identify a major contributor to this gap: contextual errors.

They explain that medical AI models may produce responses that are useful and correct to an extent but are not necessarily accurate for the specific context in which the models are being used — which include things like medical specialty, geographic location, and socioeconomic factors.

“This is not a minor fluke,” said Zitnik, who is also associate faculty at the Kempner Institute for the Study of Natural and Artificial Intelligence at Harvard University. “It is a broad limitation of all the types of medical AI models that we are developing in the field.”

In a conversation with Harvard Medicine News, Zitnik explains how contextual errors happen in medical AI models, how researchers might overcome this and other challenges, and what else she sees on the horizon for AI in medicine. This interview has been edited for length and clarity.

Harvard Medicine News: Why do contextual errors happen? How can they be fixed?

Marinka Zitnik: We think that they happen because important information for making clinical decisions is not contained in the datasets that are used to train medical AI models. The models then generate recommendations that seem reasonable and sensible but are not actually relevant or actionable for patients.

For medical AI models to perform better, they need to adapt their recommendations in real time based on specific contextual information. We suggest incorporating such information into the datasets used to train models. Additionally, we call for enhanced computational benchmarks (standardized test cases) to test models after training. Finally, we think information about context should be incorporated into the architecture, or structural design, of the models. These three steps will help ensure that models can take different contexts into account and that errors are detected before models are implemented in actual patient-care settings.

HMNews: You give three examples of how a lack of context can lead to errors in medical AI models. Can you expand on them?

Zitnik: Let’s start with medical specialties. Patients may have complex symptoms that span multiple specialties. If a patient comes to the emergency department with neurological symptoms and breathing problems, they might be referred to a neurologist followed by a pulmonologist. Each specialist brings deep expertise shaped by their training and experience, so understandably focuses on their own organ system. An AI model trained mostly on one specialty might do the same, meaning it may provide answers based on data from the wrong specialty or miss that the combination of symptoms points to a multisystem disease.

Instead, we need to develop medical AI models trained in multiple specialties that can switch between contexts in real time to focus on whatever information is most relevant.

HMNews: What about the context of geography?

Zitnik: If a model is presented with the same question in different geographic locations and gives the same answer, that answer is likely to be incorrect because each place will have specific conditions and constraints. If a patient is susceptible to a disease that could lead to organ dysfunction or failure, the clinician would need to figure out the patient’s risk and develop a plan to manage it. However, whether that patient is in South Africa, the United States, or Sweden may make a big difference in terms of how common that disease is and what treatments and procedures are approved and available.

We envision a model that can incorporate geographic information to produce location-specific, and therefore more accurate, responses. We are working on this in our lab, and we think it could have major implications for global health.

HMNews: And the third example, the socioeconomic and cultural factors that affect a patient’s behavior?

Zitnik: Say a patient shows up in the emergency department with severe symptoms after they were previously referred to an oncologist and never made an appointment. A typical response from the ED physician might be to remind the patient to schedule the oncology appointment. However, this overlooks potential barriers such as the patient living far from the oncologist, not having reliable childcare, or not being able to miss work. These types of constraints do not explicitly exist in the patient’s electronic health record, which means they also would not be factored in by an AI model that is helping to manage the patient.

A better model would take these factors into account to offer a more realistic recommendation, perhaps by providing an option for transportation or scheduling an appointment at a time that accommodates childcare or work constraints. Such a model would increase access to care for a broader range of patients rather than reinforcing inequities.

HMNews: What other major challenges are there in medical AI implementation besides contextual errors?

Zitnik: There are many. One relates to how much patients, clinicians, regulatory agencies, and other stakeholders trust medical AI models. We need to identify mechanisms and strategies that both ensure that models are trustworthy and promote trust in these models. We think the answer has to do with building models that provide transparent and easily interpretable recommendations and that say “I don’t know” when they are not confident in their conclusions.

Another challenge relates to human-AI collaboration. Currently, many people think about human-AI interfaces in the context of chatbots, in which you type in a question and get a response. We need interfaces where people can receive responses tailored to their specific backgrounds and levels of expertise — for example, content suitable for a lay audience versus a medical expert. We also need interfaces where clinicians or patients and AI models exchange information in both directions. True collaboration means that there is a question or goal or task that an AI model has to complete, and to do that, it might need to seek more information from the user.

HMNews: What do you see as the promise of medical AI if the challenges can be overcome?

Zitnik: Some models have already had an impact by making every day medical work more efficient. For example, models are helping clinicians draft patient notes and helping researchers quickly find scientific papers that may be relevant to a clinical question.

I am especially excited about the opportunities AI models can create for improving treatment. Models that can switch contexts could adjust their outputs based on the information that is most useful during different parts of the treatment process. For example, a model might shift from analyzing symptoms to suggesting possible causes to providing evidence about treatments that worked in similar patients. A model might then pivot to providing practical information about a patient’s prior medications, potential drug side effects, and what treatments are actually available. If this is done well, it could help clinicians tailor treatment decisions for complex patients with multiple conditions and medications that may fall outside standard treatment guidelines.

HMNews: How do we ensure that medical AI models are doing more good than harm?

Zitnik: I certainly think that AI in health care is here to stay. This technology, while imperfect, is already being used, so everyone in the medical AI community needs to work together to ensure that it is being developed and implemented in a responsible way. This includes considering real-world applications as we design and refine models, doing real-world testing to understand where models succeed and where they fall short, and developing guidelines for how models should be deployed. I feel optimistic that if AI researchers are aligned in the development of these models and we ask the right questions, we can detect any issues early on.

Ultimately, I think there will be many opportunities for medical AI models to improve the efficiency of medical research and clinical work and improve care for patients.

Authorship, Funding, Disclosures

Additional authors on the paper include Michelle M. Li, Ben Y. Reis, Adam Rodman, Tianxi Cai, Noa Dagan, Ran D. Balicer, Joseph Loscalzo, and Isaac S. Kohane.

Support for the research was provided by the Ivan and Francesca Berkowitz Family Living Laboratory Collaboration at HMS and Clalit Research Institute; the National Institutes of Health (grant R01HD108794); the National Science Foundation (CAREER 2339524); the Department of Defense (FA8702-15-D-0001); ARPA-H (BDF program); the Chan Zuckerberg Initiative; the Bill & Melinda Gates Foundation INV-079038; Amazon Faculty Research; the Google Research Scholar Program; AstraZeneca Research; the Roche Alliance with Distinguished Scientists; Sanofi iDEA-TECH; Pfizer Research; the John and Virginia Kaneb Fellowship Award at HMS; a Biswas Family Foundation Computational Biology Grant; a Dean’s Innovation Award for the Use of Artificial Intelligence in Education, Research, and Administration at HMS; the Harvard Data Science Initiative; and the Kempner Institute.

---

Journal

Nature Medicine

DOI

10.1038/s41591-025-04184-7 

Article Title

Scaling medical AI across clinical contexts

Article Publication Date

3-Feb-2026