Machine learning for hospital care at home

Reference number
Coordinator KUNGLIGA TEKNISKA HÖGSKOLAN - Institutionen för Medicinteknik och Hälsosystem
Funding from Vinnova SEK 172 000
Project duration March 2019 - December 2019
Status Ongoing
Venture Personal mobility between societal sectors
Call Funding for staff exchange and artificial intelligence (AI)

Purpose and goal

Using home visits, sensors, and advanced data analytics based on AI and machine learning, there is an opportunity to send more patients home earlier after a hospital visit, including chronic patients. The long-term goal is to create effective, consistent, and seamless smart digital solutions based on sensors and AI for “hospital at home” and to make this available to as many different patients as possible. To reach there, decision support systems are required for when to send patients home and then algorithms that can detect early warning signs.

Expected results and effects

We do this in order to reduce hospital costs, shorten hospital admission queues, maximize the life quality of patients during treatment, better handle chronic patients with multiple comorbidities, and earlier detect worsening conditions so that earlier interventions can take place. Foremost, the project needs to investigate the possibility to use AI and to develop AI suited to care, including answering questions such as what needs and requirements do home hospital care pose, when is AI sufficiently reliable, and certification issues.

Planned approach and implementation

In this project, a new collaboration between Karolinska University Hospital IT and KTH Royal Institute of Technology, Department of Biomedical Engineering and Health Systems will be initiated in order to achieve “hospital at home”. We will investigate needs, requirements, and opportunities around the use of AI and IoT in home hospital care through exchange of staff.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 27 October 2018

Reference number 2018-04349

Page statistics