Applying Artificial Intelligence in Developing Personalized and Sustainable Healthcare for Spinal Disorders (AID-Spine, part I)

Spinal disorders has prevailed as the leading cause of non-fatal health loss worldwide for nearly three decades. The persistence of spinal disorders is concerning given the considerable challenges to health systems and economies not equipped to care for the increase in prevalence in an ageing population in most western world. Despite advancements in assessment and treatment methods for spinal disorders, the effect of most surgical and non-surgical treatments remains to be small to moderate. Large inter-individual variation in prognosis and response to treatment partly explain the modest effects, but most of the variation between individuals is due to unknown or unmeasured factors. Inter-individual differences include both genetic and environmental factors and contain a complex picture to address for health care providers. There is lack of feasible and precise clinical prognostic tools which can help patients and clinicians to make better decisions and ensure more personalized treatments. The primary objective of AID-Spine part I is to use machine learning methods on large survey and health register data to identify people with different treatment trajectories and health outcomes after surgical and/or conservative treatment for spinal disorders. Secondary objectives are to 1) conduct external validation of the prediction models in data sets from Denmark and Sweden, and 2) explore how the prediction models can be implemented into AI-based clinical co-decision tools and interventions. The overarching aim of the AID-Spine project is to address health and welfare challenges in spinal disorders by aiming for a future personalized and sustainable healthcare. AID-Spine project members cover a broad interdisciplinary group, including neurosurgeons, physical therapists, data scientists, epidemiologists, statisticians, a user panel, and clinicians working with spinal disorders.

Spinal disorders has prevailed as the leading cause of non-fatal health loss worldwide for nearly three decades. The persistence of spinal disorders is concerning given the considerable challenges to health systems and economies not equipped to care for the increase in prevalence in an ageing population in most western world. Despite advancements in assessment and treatment methods for spinal disorders, the effect of most surgical and non-surgical treatments remains to be small to moderate. Large inter-individual variation in the course of symptoms, prognosis, and response to treatment partly explain the modest effects, but most of the variation between individuals is due to unknown or unmeasured factors. Inter-individual differences include both genetic and environmental factors and contain a complex picture to address for health care providers. There is lack of feasible and precise clinical prognostic tools which can help patients and clinicians to make better decisions and ensure more personalized treatments. In this project, we will use existing health data, administrative register data and public health surveys to generate new knowledge on risk and prognostic models for different health outcomes after receiving surgical and/or conservative treatment for spinal disorders. We will also explore users’ perspectives regarding how the externally validated risk/prognostic models can be implemented into AI-based clinical co-decision solutions. The project members and scientific board members in the AID-Spine represent a broad interdisciplinary group, including neurosurgeons, physical therapists, data scientists, epidemiologists, one expert in human-centered informatics (humanities), statisticians, a user panel, and clinicians working with spinal disorders. All research questions and topics in the AID-Spine project is based on users’ needs. Both patients and clinicians will provide feedback in all stages of the project.