Over the last decades, many prognostic models based on artificial intelligence techniques have been used to provide detailed predictions in healthcare. Unfortunately, the real-world observational data used to train and validate these models are almost always affected by biases that can strongly impact the outcomes validity: two examples are values missing not-at-random and selection bias. Addressing them is a key element in achieving transportability and in studying the causal relationships that are critical in clinical decision making, going beyond simpler statistical approaches based on probabilistic association. In this context, we propose a novel approach that combines selection diagrams, missingness graphs, causal discovery and prior knowledge into a single graphical model to estimate the cardiovascular risk of adolescent and young females who survived breast cancer. We learn this model from data comprising two different cohorts of patients. The resulting causal network model is validated by expert clinicians in terms of risk assessment, accuracy and explainability, and provides a prognostic model that outperforms competing machine learning methods.

Bernasconi, A., Zanga, A., Lucas, P., Pijnenborg, H., Reijnen, C., Scutari, M., et al. (In corso di stampa). Towards a Transportable Causal Network Model Based on Observational Healthcare Data. Intervento presentato a: HC@AIxIA 2023 : 2nd AIxIA Workshop on Artificial Intelligence For Healthcare, Roma, Italia.

Towards a Transportable Causal Network Model Based on Observational Healthcare Data

Alice Bernasconi
Primo
;
Alessio Zanga
Secondo
;
Fabio Stella
Ultimo
In corso di stampa

Abstract

Over the last decades, many prognostic models based on artificial intelligence techniques have been used to provide detailed predictions in healthcare. Unfortunately, the real-world observational data used to train and validate these models are almost always affected by biases that can strongly impact the outcomes validity: two examples are values missing not-at-random and selection bias. Addressing them is a key element in achieving transportability and in studying the causal relationships that are critical in clinical decision making, going beyond simpler statistical approaches based on probabilistic association. In this context, we propose a novel approach that combines selection diagrams, missingness graphs, causal discovery and prior knowledge into a single graphical model to estimate the cardiovascular risk of adolescent and young females who survived breast cancer. We learn this model from data comprising two different cohorts of patients. The resulting causal network model is validated by expert clinicians in terms of risk assessment, accuracy and explainability, and provides a prognostic model that outperforms competing machine learning methods.
slide + paper
Causal discovery, Causal networks, Transportability, Missing values, Selection bias
English
HC@AIxIA 2023 : 2nd AIxIA Workshop on Artificial Intelligence For Healthcare
2023
In corso di stampa
https://sites.google.com/unical.it/hcaixia2023/program-and-accepted-papers
none
Bernasconi, A., Zanga, A., Lucas, P., Pijnenborg, H., Reijnen, C., Scutari, M., et al. (In corso di stampa). Towards a Transportable Causal Network Model Based on Observational Healthcare Data. Intervento presentato a: HC@AIxIA 2023 : 2nd AIxIA Workshop on Artificial Intelligence For Healthcare, Roma, Italia.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/450261
Citazioni
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
Social impact