Details

Autor(en) / Beteiligte

• Rabhi, Sara
• Blanchard, Frédéric
• Diallo, Alpha Mamadou
• Zeghlache, Djamal
• Lukas, Céline
• Berot, Aurélie
• Delemer, Brigitte
• Barraud, Sara

Titel

Temporal deep learning framework for retinopathy prediction in patients with type 1 diabetes

Ist Teil von

• Artificial intelligence in medicine, 2022-11, Vol.133 (C), p.102408-102408, Article 102408

Ort / Verlag

Elsevier B.V

Erscheinungsjahr

2022

Link zum Volltext

Quelle

ScienceDirect

Beschreibungen/Notizen

• The adoption of electronic health records in hospitals has ensured the availability of large datasets that can be used to predict medical complications. The trajectories of patients in real-world settings are highly variable, making longitudinal data modeling challenging. In recent years, significant progress has been made in the study of deep learning models applied to time series; however, the application of these models to irregular medical time series (IMTS) remains limited. To address this issue, we developed a generic deep-learning-based framework for modeling IMTS that facilitates the comparative studies of sequential neural networks (transformers and long short-term memory) and irregular time representation techniques. A validation study to predict retinopathy complications was conducted on 1207 patients with type 1 diabetes in a French database using their historical glycosylated hemoglobin measurements, without any data aggregation or imputation. The transformer-based model combined with the soft one-hot representation of time gaps achieved the highest score: an area under the receiver operating characteristic curve of 88.65%, specificity of 85.56%, sensitivity of 83.33% and an improvement of 11.7% over the same architecture without time information. This is the first attempt to predict retinopathy complications in patients with type 1 diabetes using deep learning and longitudinal data collected from patient visits. This study highlighted the significance of modeling time gaps between medical records to improve prediction performance and the utility of a generic framework for conducting extensive comparative studies. •We propose a deep learning framework for modeling irregular medical time series.•We represent time as an input feature and as a learnable parameter of the neural network.•We validate our framework on the HbA1C time series derived from a French database.•We conduct a comparative study of Transformer-based and LSTM-based sequential models.