Poster Presentation Clinical Oncology Society of Australia Annual Scientific Meeting 2023

Dashboards to deliver data-driven dietetics in the digital age: Translation of evidence-based nutrition guidelines into practice (#164)

Merran Findlay 1 2 3 4 5 6 , Georgina Kennedy 5 6 7 , Angela Sita 8 , Tim Churches 5 , Nasreen Kaadan 7 9 , Geoff P Delaney 5 6 9 , Winston Liauw 10 11 , Katherine Bell 9 , Joanna Fardell 5 6 , Judith D Bauer 12 , Meera Agar 5 6 13
  1. Cancer Care Research Unit, Susak Wakil School of Nursing and Midwifery, The University of Sydney, Sydney, NSW, Australia
  2. Cancer Services, Royal Prince Alfred Hospital, Sydney Local Health District, Sydney, NSW, Australia
  3. The Daffodil Centre, The University of Sydney - a joint venture with Cancer Council NSW, Sydney, NSW, Australia
  4. Chris O'Brien Lifehouse, Sydney, NSW, Australia
  5. South Western Clinical School, University of NSW, Sydney, NSW, Australia
  6. Maridulu Budyari Gumal (SPHERE) Cancer Clinical Academic Group, University of NSW, Sydney, NSW, Australia
  7. Ingham Institute for Applied Medical Research, Liverpool, NSW, Australia
  8. Centre for Big Data Research in Health, University of New South Wales, Sydney, NSW, Australia
  9. Liverpool & Macarthur Cancer Therapy Centres, South Western Sydney Local Health District,, Liverpool, NSW, Australia
  10. School of Clinical Medicine, Faculty of Medicine and Health, University of NSW, Sydney, NSW, Australia
  11. Cancer Care Centre, St George Hospital, Sydney, NSW, Australia
  12. Department of Nutrition, Monash University, Melbourne, VIC, Australia
  13. Faculty of Health, University of Technology, Sydney, NSW, Australia

Aims

Healthcare dashboards visualise patient-level and aggregate data, to guide decision-making, evaluate outcomes and reveal unwarranted variations in care. We have successfully demonstrated the technical feasibility of extracting and visualising near real-time evidence-based nutrition care data comprising nutritional status and involuntary weight loss in dynamic, automated dashboards. Next, we aimed to explore the interaction of nutrition care metrics with medical and supportive care within the context of outcome variation, including visualisation throughout the care trajectory.

Methods

The SPHERE Cancer Variation (CaVa) platform extracts and harmonises data from South Western Sydney Local Health District clinical information systems, including key named entities from free text clinical notes using Natural Language Processing (NLP). Novel harmonised clinical nutrition data were evaluated for quality, completeness, generalisability and alignment with patient outcomes and quality metrics against other prognostic factors including diagnostic and treatment episodes, dietetic resource utilisation and best-practice nutrition care in near real-time.

Results

Nutrition care dashboards comprising multiple data visualisations were deployed within the CaVa modular dashboard framework. Technical and functional feasibility at both aggregate and individual patient levels was demonstrated, in anticipation of supporting use cases covering daily clinical use, periodic clinical quality reviews and health service-level monitoring. This dashboard framework has now been successfully extended, with components reused across high nutrition-risk groups, confirming suitability for sustainable live deployment. Prototype dashboards created to assess utility of this framework for the nutrition care of patients with head and neck, lung or upper gastrointestinal cancers will be presented.

Conclusion

We have established a repeatable dashboard framework that can be co-designed and adapted for multiple contexts. This pilot has demonstrated timely visualisation of evidence-based nutrition care processes and prognostic nutrition outcomes is feasible. Adoption of automated nutrition care dashboards in routine care holds potential to inform decision-making and improve patient care and outcomes.