Twelve key challenges in medical machine learning and solutions

Ellis, Randall J.; Sander, Ryan; Limon, Alfonso

doi:10.1016/j.ibmed.2022.100068

Cited by 33 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The significance of XAI in healthcare is profound as it ensures both healthcare practitioners and patients can trust and understand AI-driven decisions, [25]. Though predictive analytics have shown promise, they also come with challenges, [26]. Data quality, missing values, and class imbalances have been cited as some of the significant challenges in healthcare predictions, [27,28].…”

Section: Related Workmentioning

confidence: 99%

Inhospital Mortality, Readmission, and Prolonged Length of Stay Risk Prediction Leveraging Historical Electronic Health Records

Bopche,

Gustad,

Afset

et al. 2024

Preprint

View full text Add to dashboard Cite

Objective: The aim of this study was to investigate predictive capabilities of historical records of patients maintained at hospitals towards predicting an impending adverse outcomes such as, mortality, readmission, and prolonged length of stay (PLOS). Methods: Leveraging a de-identified dataset from a tertiary care university hospital, we developed a eXplainable Artificial Intelligence (XAI) framework combining tree-based and traditional ML models with interpretations, and statistical analysis of predictors of mortality, readmission, and PLOS. Results: Our framework demonstrated exceptional predictive performance with notable Area Under the Receiver Operating Characteristic (AUROC) of 0.9625 and Area Under the Precision-Recall Curve (AUPRC) of 0.8575 for 30-day mortality at discharge and an AUROC of 0.9545 and AUPRC of 0.8419 at admission. For the readmission and PLOS risk the highest AUROC achieved were 0.8198 and 0.9797 repectively. The tree-based machine learning (ML) models consistently outperformed the traditional ML models in all the four prediction tasks. The key predictors were age, derived temporal features, routine laboratory tests, and diagnostic and procedural codes. Conclusion: The study underscores the potential of leveraging medical history for enhanced predictive analytics in hospitals. We present a accurate and intuitive framework for early warning models that can be easily implemented in the current and developing digital health platforms to accurately predict adverse outcomes.

show abstract

Section: Related Workmentioning

confidence: 99%

Inhospital Mortality, Readmission, and Prolonged Length of Stay Risk Prediction Leveraging Historical Electronic Health Records

Bopche,

Gustad,

Afset

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…If either the domains and distributions or the tasks in both the source and target are dissimilar, the CL method is mostly unproper to develop accurate prediction models. In addition, there are four main challenges that arise when users attempt to develop accurate and reliable ML prediction models based on the CL approach [31]:…”

Section: Why the Transfer Learning Techniquementioning

confidence: 99%

“…(3) decision fusion, performed as a postprocessing step to increase the performance and reduce the prediction error rate. The effectiveness of the complex computations in ML/DL methods depends on the number of samples, the sample size, the type of data, and the size and type of hardware (i.e., physical and cloud memory to store data and perform complex computations) [24,30,31]. Although the accuracy of DL methods outperforms traditional ML methods, most DL methods require big data and a huge amount of physical or cloud memory to deal with the complex and deep architectures that are required of the expensive computations, as shown in Figure 2.…”

Section: Introductionmentioning

confidence: 99%

“…Within the domain of DH, the availability of insufficient data can present challenges to the development of efficient ML prediction models. These data challenges include various factors, such as limited data availability, data imbalance, concerns about data quality and consistency, and constraints on data access and sharing [31,207]. In the context of DH, dataset constraints related to limited samples, especially for rare diseases or conditions, can complicate the generalization of ML models based on CL.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Survey of Transfer Learning Approaches in the Machine Learning of Digital Health Sensing Data

Chato,

Regentova

2023

JPM

View full text Add to dashboard Cite

Machine learning and digital health sensing data have led to numerous research achievements aimed at improving digital health technology. However, using machine learning in digital health poses challenges related to data availability, such as incomplete, unstructured, and fragmented data, as well as issues related to data privacy, security, and data format standardization. Furthermore, there is a risk of bias and discrimination in machine learning models. Thus, developing an accurate prediction model from scratch can be an expensive and complicated task that often requires extensive experiments and complex computations. Transfer learning methods have emerged as a feasible solution to address these issues by transferring knowledge from a previously trained task to develop high-performance prediction models for a new task. This survey paper provides a comprehensive study of the effectiveness of transfer learning for digital health applications to enhance the accuracy and efficiency of diagnoses and prognoses, as well as to improve healthcare services. The first part of this survey paper presents and discusses the most common digital health sensing technologies as valuable data resources for machine learning applications, including transfer learning. The second part discusses the meaning of transfer learning, clarifying the categories and types of knowledge transfer. It also explains transfer learning methods and strategies, and their role in addressing the challenges in developing accurate machine learning models, specifically on digital health sensing data. These methods include feature extraction, fine-tuning, domain adaptation, multitask learning, federated learning, and few-/single-/zero-shot learning. This survey paper highlights the key features of each transfer learning method and strategy, and discusses the limitations and challenges of using transfer learning for digital health applications. Overall, this paper is a comprehensive survey of transfer learning methods on digital health sensing data which aims to inspire researchers to gain knowledge of transfer learning approaches and their applications in digital health, enhance the current transfer learning approaches in digital health, develop new transfer learning strategies to overcome the current limitations, and apply them to a variety of digital health technologies.

show abstract

“…Convolutional neural networks (CNNs) have proven successful in this task due to their ability to process images effectively (Shen et al, 2017). However, supervised approaches that use CNNs have limitations, such as the need for large amounts of expert-annotated training data and the challenge of learning from noisy or imbalanced data (Ellis et al, 2022;Karimi et al, 2020;Johnson and Khoshgoftaar, 2019). Unsupervised anomaly detection (UAD) is an alternative approach that can be trained with healthy samples only, eliminating the need for pixel-level annotations.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Anomaly Detection in 3D Brain MRI Using Deep Learning with Impured Training Data

Behrendt¹,

Bengs²,

Frederik³

et al. 2022

2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)

View full text Add to dashboard Cite

The detection of lesions in magnetic resonance imaging (MRI)-scans of human brains remains challenging, timeconsuming and error-prone. Recently, unsupervised anomaly detection (UAD) methods have shown promising results for this task. These methods rely on training data sets that solely contain healthy samples. Compared to supervised approaches, this significantly reduces the need for an extensive amount of labeled training data. However, data labelling remains error-prone. We study how unhealthy samples within the training data affect anomaly detection performance for brain MRI-scans. For our evaluations, we consider three publicly available data sets and use autoencoders (AE) as a well-established baseline method for UAD. We systematically evaluate the effect of impured training data by injecting different quantities of unhealthy samples to our training set of healthy samples from T1-weighted MRI-scans. We evaluate a method to identify falsely labeled samples directly during training based on the reconstruction error of the AE. Our results show that training with impured data decreases the UAD performance notably even with few falsely labeled samples. By performing outlier removal directly during training based on the reconstruction-loss, we demonstrate that falsely labeled data can be detected and removed to mitigate the effect of falsely labeled data. Overall, we highlight the importance of clean data sets for UAD in brain MRI and demonstrate an approach for detecting falsely labeled data directly during training.

show abstract

Twelve key challenges in medical machine learning and solutions

Cited by 33 publications

References 15 publications

Inhospital Mortality, Readmission, and Prolonged Length of Stay Risk Prediction Leveraging Historical Electronic Health Records

Inhospital Mortality, Readmission, and Prolonged Length of Stay Risk Prediction Leveraging Historical Electronic Health Records

Survey of Transfer Learning Approaches in the Machine Learning of Digital Health Sensing Data

Unsupervised Anomaly Detection in 3D Brain MRI Using Deep Learning with Impured Training Data

Contact Info

Product

Resources

About