- add category, category 2, Deep dives
Deep dives
Hospital at home
Hospitalization at home (HAD) is emerging as an innovative solution to the challenges of an aging population and the growing demand for personalized care. In 2025, this model is taking on a new dimension in Switzerland, driven by a desire for systemic transformation and the digitization of the healthcare system. It is also a concept that appeals to patients who have been able to test it.
This Deep Dive draws on the testimonies, feedback and analyses of Swiss and international experts gathered at the Digital Health Connect 2024 conference to provide an in-depth overview of the challenges, achievements and prospects of the home hospitalization model in Switzerland.
Home care in a context of demographic transition
Switzerland, like many countries, is experiencing a significant increase in its so-called “senior” population, with 19.4% of its population aged over 64 in 2024. This ageing is accompanied by an increase in degenerative and chronic diseases, putting hospital infrastructures under increasing pressure.
According to the CollHome study, the desire to grow old at home is widely shared by 90% of senior citizens. Between 2013 and 2022, the number of patients receiving home care has increased by 84%.
One of the solutions to this problem lies in conceptualizing the home as a care environment.
Chloé Schorderet, scientific assistant at the University of Applied Sciences and Arts Valais/Wallis
The “Hospital at Home” model: a paradigm shift
The concept of the hospital at home originated in the United States and is now well established in many countries.
Hospitalization at home involves hospital-level care and infrastructure, including specialized medical and nursing staff, digital solutions that facilitate the transmission of shared data and telemedicine, acute examinations and treatments, as well as high-quality standards.
Being at patients’ homes implies a change of approach.
The idea is to move hospital care to the home and provide acute care treatment there in a multidisciplinary manner, in partnership with external stakeholders.
Laura Treccani, member of the board of directors of the Swiss Hospital at Home Society
Laura Treccani is convinced of it: “Hospital-at-Home is not only a response to the Covid-19 pandemic, but also a real transformation of the care model.
Some caregivers have to take off their shoes before entering. The degree of ‘power’ is thus different.
Henrik Bjärtun, specialist in internal medicine and co-founder of the start-up Medoma
Feedback: three pilot projects in Switzerland
In Switzerland, several establishments have launched pilot home hospitalization projects, thus laying the foundation for a structural change in patient care, as shown in the infographic of the Swiss Hospital at Home Society below.
Three initiatives, led by committed actors, concretely illustrate the possibilities and challenges of the model:
Hospital-at-Home at the Arlesheim Clinic
- Basel-Landschaft
Since its launch, this project, which has become a fully-fledged service, has treated 290 patients in 18 months, with three daily visits, including one interprofessional visit, combined with remote monitoring.
It emphasizes the importance of allowing patients to choose between hospital and home, of adapting hospital protocols and of adapting to the specific needs of patients, which are key elements for the success of this transition.
It’s about finding people who like this new approach and who dare to think differently.
We4You in Einsiedeln
- Schwytz
The We4You network, based in Einsiedeln, is based on an integrated holistic approach and interdisciplinary collaboration.
Her ambition is to break down professional silos and build a common culture of care. She advocates for decompartmentalization of healthcare professions, a rethinking of traditional practices, and a refocusing on coordination around the patient. She emphasizes the need to train the new generation of caregivers to approach the care relationship differently.
Claudia Günzel, director of the Spitex Höfe care network in the Pfäffikon region, points out that the success of such projects depends on better communication between the various stakeholders and the importance of integrating home services such as Spitex.
The patient tells us what they need and we discuss what we should do.
Dr. Kerstin Schlimbach, doctor in charge of We4You
Patient@home at the Biel Hospital
- Bern
Through the Patient@home project, the Biel Hospital Center (CHB) aims to provide certain acute care services directly to patients’ homes. The system provides for 24/7 monitoring via a digital platform, provided by CHB doctors using telemedicine, while on-site care is provided by partners such as home care services (ASD).
It reiterates the importance of sharing knowledge and emphasizes the need to settle the issue of invoicing and pricing, with the collaboration of the health insurance funds.
Let’s not reinvent the wheel separately, but work together.
Gianni Imbriani, Head of the Project Management Office at the Centre Hospitalier de Bienne
The advantages of hospitalization at home
Home care encourages changes to infrastructure, while also making it possible to include new digital technologies. Primary care and doctors continue to play an essential role.
Improvement of the quality of life of patients
Hospital at Home allows patients to receive care in a familiar environment, contributing to their psychological well-being and faster recovery. Patients retain their autonomy and maintain their social ties, which are essential factors for their overall health.
A study from February 2025, conducted at the University Clinic for Child and Adolescent Psychiatry and Psychotherapy of the University Psychiatric Services Bern (UPD) and the University of Bern, emphasizes that therapy at home is more effective than a stay in a clinic. The young patients treated at home as part of the AT_HOME pilot project had significantly fewer psychiatric symptoms than those who received treatment in a hospital setting.
Patients feel better and safer at home.
Henrik Bjärtun, specialist in internal medicine and co-founder of the company Medoma
According to him, thanks to home hospitalization, patients are also more involved in their care and have a better understanding of their condition, while sleeping and eating better.
Reduction of healthcare costs
Hospital at home has economic advantages in that it reduces the length of hospital stays and the number of readmissions, thus contributing to better management of hospital resources.
A study published in Nature Medicine in 2022 showed that up to 40% savings are possible thanks to lower infrastructure costs and shorter treatment times.
Case Study: Saving thousands of days of hospitalization
During the 12th edition of the Digital Health Connect conference. Prof. Daniel Lasserson, Consultant Physician in the Department of Geriatric Medicine at the John Radcliffe Hospital at Oxford University Hospitals, explains that for the 3,000 patients treated by his team in the United Kingdom, 14,000 days of hospitalization have been saved, representing approximately 800,000 pounds sterling for a single hospital in one year. The death rate during home treatment is also very low, and the home hospital also makes it possible to provide care during the last year of life, when 80% of medical expenses are incurred.
Prevention of nosocomial infections
In Switzerland, 6% of patients contract an infection in hospital. By avoiding prolonged hospital stays, HAH reduces the risk of nosocomial infections, a major public health issue as highlighted by this research from the University Hospital of Madrid.
The challenges of home hospitalization
Several challenges arise when home hospitalization is considered. The major obstacles are: change management and reimbursement.
Interprofessional collaboration
Interprofessional collaboration remains a major challenge in the context of home care.
Providing home hospitalization care relies on close collaboration between doctors, nurses, occupational therapists, pharmacists and other stakeholders.
But in French-speaking Switzerland, the CollHome study, led by the HES-SO Valais-Wallis, reveals that exchanges are too often limited to the transmission of information, without any real systematic coordination. Among the obstacles identified are working outside the institution, lack of time, lack of recognition for collaborative activities and the persistence of rigid professional hierarchies.
There is an evolution in the caregiving function: doctors and caregivers are joining forces in an integrated collaboration and seeing a transformation of their role, with less medical hierarchy.
Laura Treccani, member of the board of directors of the Swiss Hospital at Home Society
We have put forward several hypotheses. Among them, the fact of working outside an institutional structure seems particularly decisive.
Chloé Schorderet, HES-SO Santé Valais/Wallis
The results do indeed show that professionals who are part of the same organisation collaborate more. This observation is confirmed by scientific literature.
In addition, other factors can influence the quality of interactions: the availability and accessibility of colleagues, but also the very perception of what constitutes “good collaboration”, which can differ between professions. Another review revealed that doctors and nurses do not always share the same criteria for evaluating the quality of their cooperation.
Reimbursement for home hospitalization: a barrier to overcome
Despite the demonstrated clinical and economic benefits, the biggest obstacle is certainly related to the fact that, in Swiss health insurance law, reimbursement for such care is not provided for. To date, no standardized national tariff covers this type of care. This considerably hinders the development of the model, forcing each pilot project to find solutions on a case-by-case basis, often through individual negotiations with insurance companies, cantons and certain support funds.
The objective would be to create new DRG (Diagnosis Related Group) packages adapted to such acute home care, which requires a political mandate, supported by evidence of the medical and economic effectiveness of the model. This data exists, but now it needs to be integrated into the decision-making process.
Within the Swiss Hospital at Home company, a working group is discussing this pricing issue. In particular, we are trying to get closer to other players, to develop models that we can present to the political world.
Laura Treccani, committee member of the Swiss Hospital at Home company, created in 2023 to promote this concept
Improving access to treatment
Detect weak signals offering opportunities for prevention
– Stroke prevention using a monitoring device
AI, a virtual nurse to answer questions about medication, schedule doctor’s visits or send reports to doctors
Support diagnosis, predictive and personalized medicine
AI is opening up new horizons by leveraging unstructured data and minimizing medical errors that can lead to death. The idea of having expertise directly accessible to the patient thanks to AI is of growing interest, even if it remains a goal yet to be achieved.
Blaise Jacholkowski, Principal Business Consultant at Zühlke
Clinical recommendations for monitoring patients suffering from depression
AI can be an effective therapeutic alternative, as a recent study points out. “Surprisingly, AIs like ChatGPT sometimes outperform humans in terms of empathy and nuanced responses, making them potentially more effective in clinical recommendations for monitoring patients suffering from depression,” explains Blaise Jacholkowski, Principal Business Consultant at Zühlke
Early detection
- of lung cancer
Led by Henning Müller and the Histopathology Department at Valais Hospital, an SNSF-supported research project aims to support healthcare professionals in detecting lung cancer and aiding diagnosis via algorithms.
- autism spectrum disorders
Led by Antoine Widmer of the HES-SO Valais/Wallis, an SNSF-supported research project is pursuing the detection of autism spectrum disorders using video games and AI.
- of stroke
Abderrahmane Hedjoudje, assistant physician in neuroradiology at Valais Hospital, explains that this technology has the potential to redefine the patient care pathway: “From the moment a patient is taken into care in the emergency department, particularly in the case of a stroke, it is important to take into account various parameters and information to ensure informed decisions. In this context, AI positions itself as a crucial tool, capable of processing this multiple data to make relevant predictions about the patient’s potential clinical course”.
Facilitating access to medical knowledge
Artificial intelligence enables breakthroughs in hitherto unexplored territory.
- Predicting protein structure from amino acid sequence with AlphaFold
- Facilitate the search and summarization of electronic health records by automatically generating a first draft of the hospital discharge narrative with Meditech
- Guiding clinical decision-making: MediTron is the world's most powerful LLM, adapted to the medical field and designed by EPFL scientists to help healthcare professionals.
Feedback: three pilot projects in Switzerland
As this technology takes off, we need to improve our interactions with LLMs (such as chatGPT) and professionalize them. Prompt engineering, which underpins design, refinement and implementation, is therefore booming and offers new job prospects.
Understanding how AI works to use it better
ChatGPT is a stochastic parrot
There isn’t one AI in healthcare, but many AIs.
We need to distinguish between deep learning networks, known as deep learning, and the “new revolution of generative AI”, which has the capacity to develop computer code itself” invites David Gruson, co-founder of EtikIA.
A generative AI is a system that takes data and generates content. An AI is therefore not there to produce coherent and fair content, but it works on a probabilistic distribution.
We shouldn’t be depressed by these contents, which are sometimes crazy. Generative AI doesn’t make sense, it generates content.
Christian Lovis, Head of the Medical Information Sciences Department at the HUG.
We mustn’t forget that ChatGPT is trained to produce answers that people like. We therefore have to check on a case-by-case basis whether the statements correspond to the state of knowledge or are biased.
Dr. rer. biol. hum. Reinhold Sojer, Head of the WFH’s Digitalization / eHealth Division.
Data digitization: a pharaonic undertaking
The disruptive events associated with the Covid pandemic have highlighted gaps and biases in data management, particularly in the reporting of positive cases. Digitization, combined with AI, represents a race ahead for the entire country. However, healthcare data faces serious obstacles.
In healthcare, the multiplicity of data from different specialties (genomics, proteomics, metabolism, microbiome, etc.) is a wealth, but interconnecting them is crucial to fully understanding the reasons behind a disease.
In clinical records, there is a huge disparity between the amount of data documented and that required for a complete understanding.
However, these data are scattered, just like human singularities.
Christian Lovis, Head of the Medical Information Sciences Department at the HUG
Between computing power and the climate crisis
LLMs don’t just consider the previous words but analyse the whole previous context. They learn continuations based on models learned elsewhere, using probability to make decisions. However, the size of the model is not enough; they need to be trained with considerable computing power to operate effectively.
Andrei Kucharavy, co-founder of the Gen Learning Lab at HES-SO Valais/Wallis.
What’s more, the impact of digital technology on climate change – to which the meteoric rise of artificial intelligence is contributing through its growing demand for energy – is becoming urgent to limit.
According to an article published by the CNRS (French National Centre for Scientific Research), reactions to this issue are not very strong today:
“Humanity is still sticking to the recipe that says the bigger a model is, the better it is. But this is a very inefficient way of proceeding. We also know that there is considerable scope for progress in terms of efficiency, even if we haven’t yet found the scientific keys to unlocking this potential.
Obstacles
& risks
The use of artificial intelligence (AI) in healthcare can entail risks, particularly in terms of security, privacy and the dignity of the individuals concerned.
Potential incidents can lead to serious repercussions for the individuals whose data is involved, including such things as unwanted targeting of their profile, phishing attempts based on their medical data, identity theft, or discriminatory treatment of their requests from providers outside the medical field.
Large language models such as the one used by ChatGPT could soon become essential tools for diagnosing and treating patients. But adjustments are still needed, because according to the diverse scientific literature on the subject, diagnoses and treatment recommendations may turn out to be erroneous or inappropriate, with serious consequences for patients.
Dr. med. François Bastardot, MSc, physician in charge of the Clinical Information System, Vaud University Hospital (CHUV) in the Swiss Doctors’ Bulletin.
Prof. Dr. med. Claudia M. Witt, Professor of Complementary and Integrative Medicine and Director of the Digital Society Initiative at the University of Zurich, in the Swiss Doctors’ Bulletin.
Conclusion
Huge potential...
to be used with lucidity!
Christian Lovis insists on the need to move from simple raw data to a deeper semantic understanding in order to build relevant healthcare models. “We need to make things relevant, and that requires clinicians and patients too!
Challenges persist in the effective use of healthcare data and AI, requiring a holistic approach and a deep understanding of the nuances of data to truly revolutionize medicine.
Blaise Jacholkowski stresses the crucial importance of putting safeguards in place to ensure the credibility and reliability of the information provided by these AI systems. While regulation in this field is still in progress, the emergence of models such as Med.PaLM 2, dedicated to healthcare and tested in renowned institutions such as the Mayo Clinic, demonstrate the constant evolution of this technology.
Blaise Jacholkowski envisions a patient journey of the future, where AI will be integrated at every stage, from online consultation to home interactions for recovery, paving the way for more targeted and precise care.
Governments and regulators around the world are working on regulations to frame the use of AI in healthcare.
