New digital decision support gives gravely ill cancer patients the right fracture treatment
Jonathan Forsberg and Rikard Wedin, both members of the Orthopaedics research group, have developed an adaptive clinical decision support system, PATHFx, to help gravely ill cancer patients get the right treatment of fractures. PATHFx is based on artificial intelligence (AI) combined with data from Swedish research registers. The project uses technology to facilitate everyday medical care and will benefit the patients and reduce healthcare costs for a very vulnerable patient group.
Each year, 10,000 patients in Sweden are diagnosed with bone metastasis. Breast and prostate cancer are among the types of cancer to most frequently spread through metastases to the bone, and more than half of the patients with advanced stages of cancer have severe complications due to their bone metastases. Common complications include pain, fractures, and paralysis due to vertebral metastases putting pressure on the spinal cord. Determining which surgical treatments are relevant is a complicated decision with major consequences for the patient’s quality of life in their final days.
“The adaptive treatment support PATHFx uses a survival prognoses to aid the orthopaedic surgeon’s decision-making regarding whether to offer the patient surgery, and which implants are suitable. It also helps avoid under-treatment and over-treatment. The goal is to optimise the functioning of each patient’s body and their quality of life for as long as possible,” says Rikard Wedin, chief physician at the orthopaedic clinic at Karolinska University Hospital and docent at the Department of Molecular Medicine and Surgery, Karolinska Institutet.
International Bone Metastasis Registry
PATHFx is linked via Regional Cancer Centre Stockholm/Gotland to the International Bone Metastasis Registry in order to continually improve and update its prognoses as new cancer treatments are introduced. Through constant development, PATHFx will be able to provide reliable survival prognoses to all patients with bone metastasised cancer, which will give patients and doctors better guidance in when complication-laden and costly treatments and investigations are justified at the end stages of the disease. To further improve the decision-making data, a reference library is being constructed on the PATHFx website where leading cancer centres share proposed treatments of difficult cases.
Currently, the patient data includes sources from Sweden, USA, Japan, Finland, and South Africa, and in the near future Singapore, Italy, Denmark, and Scotland will be added.
PATHFx has proven to be very clinically useful at the orthopaedic clinic at Karolinska University Hospital. An integration into patient journals has already been done by the National Institutes of Health, USA. PATHFx is thoroughly externally validated in the Nordic countries, Italy and Japan, and has proven to provide reliable survival prognoses.
PATHFx has been developed as part of Jonathan Forsberg’s doctoral thesis Turning data into decisions : clinical decision support in orthopaedic oncology. The work is funded by Stockholm County Council’s innovation fund, KI Innovation, and the Percy Falk Foundation.
PATHFx was nominated for the Sveapriset award during the Kvalitetsmässan expo and was named one of Sweden’s 5 best e-health innovations in 2017.
Can A Multivariate Model for Survival Estimation in Skeletal Metastases (PATHFx) Be Externally Validated Using Japanese Patients?
Clin. Orthop. Relat. Res. 2017 Sep;475(9):2263-2270
Treating metastatic disease: Which survival model is best suited for the clinic?
Clin. Orthop. Relat. Res. 2013 Mar;471(3):843-50
Can We Estimate Short- and Intermediate-term Survival in Patients Undergoing Surgery for Metastatic Bone Disease?
Clin. Orthop. Relat. Res. 2017 Apr;475(4):1252-1261
How do we estimate survival? External validation of a tool for survival estimation in patients with metastatic bone disease-decision analysis and comparison of three international patient populations.
BMC Cancer 2015 May;15():424