facebook tracking

Thesis work: Machine learning prediction of hospital readmission risk

Background
There is a strong need to increase the efficiency of healthcare workflows, to improve the patient experience and optimize the usage of healthcare resources. One way to achieve this goal is to use Machine Learning techniques to predict whether a patient will have an unplanned readmission shortly after admission discharge. This project is a collaboration between Cambio Healthcare Systems (one of Scandinavia’s leading suppliers of healthcare information systems and a growing player in the European market with just over 100,000 users across general and university hospitals, specialist units and outpatient units), Region Uppsala and KTH Royal Institute of Technology.

Research problem
Anonymized data will be provided by Region Uppsala to address the challenging problem of predicting whether a patient is likely to be readmitted within e.g. a month after being discharged. A number of variables from the anonymized patient records will be available, including age, priority level, reason for admission, vital parameters, lab info, earlier diagnoses, etc. The main research question to assess is if a Machine Learning approach has better potential than an approach based on manually selected risk criteria.

In addition to the main research question the student can also explore questions such as:

  • Are there certain patient groups (e.g. a certain diagnosis or age group) which are especially relevant to focus on?
  • Which criteria are important for evaluating the model (accuracy, interpretability, complexity, compute time, etc)?
  • Which features are most important for the model?
  • Which type of hospital staff would find the model useful, and which requirements would they have on a future solution?

Importance
The project is important for the Swedish healthcare system, since there is a general lack of hospital staff/beds and healthcare providers are struggling to give all patients sufficient care while keeping down the costs of healthcare resources and staff. Unplanned readmission might indicate that a patient has not been given sufficient care or sufficient information during the hospical visit. If readmission risk can be accurately predicted, hospital resources can be better utilized and actions can be better planned.

It is expected that a machine learning approach has strong potential to provide a promising data-driven solution, which could be scaled up and tested in real-world healthcare scenarios. It remains to be seen whether the resulting inference model can combine satisfactory prediction accuracy with interpretability to ensure that doctors and nurses understand the basis and feel confident/comfortable about the prediction.

Project information
The student will be supervised by Cambio Healthcare Systems, who will guide to the Cambio COSMIC data structure, and help the student to reflect over how the model could eventually be used as part of the existing healthcare information systems.

Workshops will be conducted together with Region Uppsala to ensure that the model is built on correct assumptions and solves relevant healthcare problems. One project goal is to be able to evaluate the model performance together with Region Uppsala staff.

About Cambio
Within 6 years, the Swedish government wants to be the best in the world in E-health. At Cambio Healthcare Systems we fully support that ambition. Cambio is a leading IT company in the field of E-health.

Cambio was founded in 1993 in Linköping by two engineers with the ambition to digitizing healthcare. Today Cambio is an international company with headquarters in Stockholm, development centers in Linköping, Motala and in Sri Lanka, offices in Denmark and England. We are 600+ employees with different backgrounds, areas of expertise and tasks, but with a common goal to create world class IT solutions that contribute to the greater good within the E-health industry.

For questions about the project, please contact marcus.petersson@cambio.se.

We look forward to receiving your application!

Last day for applying: 31st of August 2019

The selection of candidates will take place continuously, therefore please apply as soon as possible.

Apply for this job

Or, know someone who would be a perfect fit? Let them know!

Cambio Healthcare Systems AB (Stockholm)

Drottninggatan 89
113 60 Stockholm Directions +46 8-691 49 00

Healthcare and social services are facing major challenges. Our population is growing and we are living longer. As a direct result, our demands for health and social care are increasing. At the same time, healthcare providers have to ensure access to high-quality and safe healthcare services, a good working environment and satisfied patients and consumers who want to become more involved, and are demanding new ways to interact. This requires a completely new model for the delivery of health care and social services.   

Cambio Healthcare Systems is Sweden’s leading suppliers of healthcare information systems and a growing player in the European market with just over 100,000 users across general and university hospitals, specialist units and outpatient units. Through the use of our integrated solutions, our customers provide services to 4 million patients.


Already working at Cambio?

Let’s recruit together and find your next colleague.

  • Carl Hildebrand
  • Clara Nazhadeian
  • Ida Linnertorp
  • Marie Ericson
  • Marie Odbom
  • Sara Sköld
Teamtailor

Applicant tracking system by Teamtailor