A machine learning model for predicting ICU readmissions and key risk factors: analysis from a longitudinal health records

Junqueira, Alvaro Ribeiro Botelho; Mirza, Farhaan; Baig, Mirza Mansoor

doi:10.1007/s12553-019-00329-0

Cited by 13 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Admit. Patient Data (QHAPDC) [62] All cause All patients 10E5 NA MIMIC III database [92] All cause 16+ 38,597 49,785 MIMIC II database [81] All cause 16+ 26,000 NA Cerner Health Facts database [100] All cause All patients 17,880,231 74,036,643 Natl. Surgical Quality Imp.…”

Section: Discussionmentioning

confidence: 99%

“…A research study [92] using Medical Information Mart for Intensive Care III (MIMIC-III) database [129] shows that, by using undersampling, their model achieves 0.642 AUC score for ICU patient readmission. Another study [63] investigates RUS sampling and five supervised learning methods, decision trees, naive bayes, logistic regression, neural networks, and support vector machines (SVM) for risk modality and hospital readmission prediction.…”

Section: Sampling Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Predictive Modeling of Hospital Readmission: Challenges and Solutions

Wang

Zhu

2021

Preprint

View full text Add to dashboard Cite

Hospital readmission prediction is a study to learn models from historical medical data to predict probability of a patient returning to hospital in a certain period, e.g. 30 or 90 days, after the discharge. The motivation is to help health providers deliver better treatment and post-discharge strategies, lower the hospital readmission rate, and eventually reduce the medical costs. Due to inherent complexity of diseases and healthcare ecosystems, modeling hospital readmission is facing many challenges. By now, a variety of methods have been developed, but existing literature fails to deliver a complete picture to answer some fundamental questions, such as what are the main challenges and solutions in modeling hospital readmission; what are typical features/models used for readmission prediction; how to achieve meaningful and transparent predictions for decision making; and what are possible conflicts when deploying predictive approaches for real-world usages. In this paper, we systematically review computational models for hospital readmission prediction, and propose a taxonomy of challenges featuring four main categories: (1) data variety and complexity; (2) data imbalance, locality and privacy; (3) model interpretability; and (4) model implementation. The review summarizes methods in each category, and highlights technical solutions proposed to address the challenges. In addition, a review of datasets and resources available for hospital readmission modeling also provides firsthand materials to support researchers and practitioners to design new approaches for effective and efficient hospital readmission prediction.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Sampling Approachesmentioning

confidence: 99%

Predictive Modeling of Hospital Readmission: Challenges and Solutions

Wang

Zhu

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…However, these augmentation strategies that are successful in computer vision cannot be easily applied to textual data due to the inherent complexity of natural language [8], where the grammatical or semantic consistency of text could hardly be preserved after transformation [9]. As to the specific task of readmission prediction, such issues, e.g., data imbalance, are either ignored [10] or processed with sampling techniques [11], such as SMOTE [12] or ROSE [13] that do not cope with textual data.…”

Section: Introductionmentioning

confidence: 99%

Textual Data Augmentation for Patient Outcomes Prediction

Dou

Nguyen

2021

2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

Deep learning models have demonstrated superior performance in various healthcare applications. However, the major limitation of these deep models is usually the lack of highquality training data due to the private and sensitive nature of this field. In this study, we propose a novel textual data augmentation method to generate artificial clinical notes in patients' Electronic Health Records (EHRs) that can be used as additional training data for patient outcomes prediction. Essentially, we fine-tune the generative language model GPT-2 to synthesize labeled text with the original training data. More specifically, We propose a teacher-student framework where we first pre-train a teacher model on the original data, and then train a student model on the GPT-augmented data under the guidance of the teacher. We evaluate our method on the most common patient outcome, i.e., the 30-day readmission rate. The experimental results show that deep models can improve their predictive performance with the augmented data, indicating the effectiveness of the proposed architecture.

show abstract