Back

Multicentric validation of a Multimorbidity Adjusted Disability Score to stratify depression-related risks using temporal disease maps

Gonzalez-Colom, R.; Mitra, K.; Vela, E.; Gezsi, A.; Paajanen, T.; Gal, Z.; Hullam, G.; Makinen, H.; Nagy, T.; Kuokkanen, M.; Piera-Jimenez, J.; Roca, J.; Antal, P.; Juhasz, G.; Cano, I.

2023-09-04 health informatics
10.1101/2023.09.04.23295005 medRxiv
Show abstract

In the EU project TRAJECTOME, we used a novel methodology to identify temporal disease maps of depression and highly prevalent co-occurring disease conditions. This information was combined with disability weights established by the Global Burden of Disease Study 2019 to create a depression-related health risk assessment tool, the Multimorbidity Adjusted Disability Score (MADS). MADS was used to stratify over one million cases from three different cohorts and evaluate the impact on utilisation of healthcare resources, mortality, pharmacological burden, healthcare expenditure and multimorbidity progression. Results indicate statistically significant associations between MADS and increased mortality rate (P <.001), heightened healthcare utilization (i.e. emergency room visits P <.001; hospitalizations P <.001; pharmaceutical prescriptions P <.001; total healthcare expenditure P <.001), and a higher risk of disease progression and incidence of new depression-related comorbidities. MADS seems to be a promising approach to predict depression-related health risk and depressions impact on individuals and healthcare systems, which can be tested in other diseases; nevertheless, clinical validation is still necessary.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.