In the Pursuit of Privacy: The Promises and Predicaments of Federated Learning in Healthcare

Exploring the values underlying machine learning research in medical image analysis

Machine learning has emerged as a crucial tool for medical image analysis, largely due to recent developments in deep artificial neural networks addressing numerous, diverse clinical problems. As with any conceptual tool, the effective use of machine learning should be predicated on an understanding of its underlying motivations just as much as algorithms or theory - and to do so, we need to explore its philosophical foundations. One of these foundations is the understanding of how values, despite being non-empirical, nevertheless affect scientific research. This article has three goals: to introduce the reader to values in a way that is specific to medical image analysis; to characterise a particular set of technical decisions (what we call the end-to-end vs. separable learning spectrum) that are fundamental to machine learning for medical image analysis; and to create a simple and structured method to show how these values can be rigorously connected to these technical decisions. This better understanding of how the philosophy of science can clarify fundamental elements of how medical image analysis research is performed and can be improved.

Clinical Decision Support for Improved Neonatal Care: The Development of a Machine Learning Model for the Prediction of Late-onset Sepsis and Necrotizing Enterocolitis

OBJECTIVE

To develop an artificial intelligence-based software system for predicting late-onset sepsis (LOS) and necrotizing enterocolitis (NEC) in infants admitted to the neonatal intensive care unit (NICU).

STUDY DESIGN

Single-center, retrospective cohort study, conducted in the NICU of the Antwerp University Hospital. Continuous monitoring data of 865 preterm infants born at <32 weeks gestational age, admitted to the NICU in the first week of life, were used to train an XGBoost machine learning (ML) algorithm for LOS and NEC prediction in a cross-validated setup. Afterward, the model's performance was assessed on an independent test set of 148 patients (internal validation).

RESULTS

The ML model delivered hourly risk predictions with an overall sensitivity of 69% (142/206) for all LOS/NEC episodes and 81% (67/83) for severe LOS/NEC episodes. The model showed a median time gain of ≤10 hours (IQR, 3.1-21.0 hours), compared with historical clinical diagnosis. On the complete retrospective dataset, the ML model made 721 069 predictions, of which 9805 (1.3%) depicted a LOS/NEC probability of ≥0.15, resulting in a total alarm rate of <1 patient alarm-day per week. The model reached a similar performance on the internal validation set.

CONCLUSIONS

Artificial intelligence technology can assist clinicians in the early detection of LOS and NEC in the NICU, which potentially can result in clinical and socioeconomic benefits. Additional studies are required to quantify further the effect of combining artificial and human intelligence on patient outcomes in the NICU.

Learning across diverse biomedical data modalities and cohorts: Challenges and opportunities for innovation

In healthcare, machine learning (ML) shows significant potential to augment patient care, improve population health, and streamline healthcare workflows. Realizing its full potential is, however, often hampered by concerns about data privacy, diversity in data sources, and suboptimal utilization of different data modalities. This review studies the utility of cross-cohort cross-category (C4) integration in such contexts: the process of combining information from diverse datasets distributed across distinct, secure sites. We argue that C4 approaches could pave the way for ML models that are both holistic and widely applicable. This paper provides a comprehensive overview of C4 in health care, including its present stage, potential opportunities, and associated challenges.

Data Science and Precision Oncology Nursing: Creating an Analytic Ecosystem to Support Personalized Supportive Care across the Trajectory of Illness

OBJECTIVES

The authors' objective is to present an overarching framework of an analytic ecosystem using diverse data domains and data science approaches that can be used and implemented across the cancer continuum. Analytic ecosystems can improve quality practices and offer enhanced anticipatory guidance in the era of precision oncology nursing.

DATA SOURCES

Published scientific articles supporting the development of a novel framework with a case exemplar to provide applied examples of current barriers in data integration and use.

CONCLUSION

The combination of diverse data sets and data science analytic approaches has the potential to extend precision oncology nursing research and practice. Integration of this framework can be implemented within a learning health system where models can update as new data become available across the continuum of the cancer care trajectory. To date, data science approaches have been underused in extending personalized toxicity assessments, precision supportive care, and enhancing end-of-life care practices.

IMPLICATIONS FOR NURSING PRACTICE

Nurses and nurse scientists have a unique role in the convergence of data science applications to support precision oncology across the trajectory of illness. Nurses also have specific expertise in supportive care needs that have been dramatically underrepresented in existing data science approaches thus far. They also have a role in centering the patient and family perspectives and needs as these frameworks and analytic capabilities evolve.

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient's pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN's RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

Guidelines and evaluation of clinical explainable AI in medical image analysis

Explainable artificial intelligence (XAI) is essential for enabling clinical users to get informed decision support from AI and comply with evidence-based medical practice. Applying XAI in clinical settings requires proper evaluation criteria to ensure the explanation technique is both technically sound and clinically useful, but specific support is lacking to achieve this goal. To bridge the research gap, we propose the Clinical XAI Guidelines that consist of five criteria a clinical XAI needs to be optimized for. The guidelines recommend choosing an explanation form based on Guideline 1 (G1) Understandability and G2 Clinical relevance. For the chosen explanation form, its specific XAI technique should be optimized for G3 Truthfulness, G4 Informative plausibility, and G5 Computational efficiency. Following the guidelines, we conducted a systematic evaluation on a novel problem of multi-modal medical image explanation with two clinical tasks, and proposed new evaluation metrics accordingly. Sixteen commonly-used heatmap XAI techniques were evaluated and found to be insufficient for clinical use due to their failure in G3 and G4. Our evaluation demonstrated the use of Clinical XAI Guidelines to support the design and evaluation of clinically viable XAI.

Current status and future developments in predicting outcomes in radiation oncology

Advancements in data-driven technologies and the inclusion of information-rich multiomics features have significantly improved the performance of outcomes modeling in radiation oncology. For this current trend to be sustainable, challenges related to robust data modeling such as small sample size, low size to feature ratio, noisy data, as well as issues related to algorithmic modeling such as complexity, uncertainty, and interpretability, need to be mitigated if not resolved. Emerging computational technologies and new paradigms such as federated learning, human-in-the-loop, quantum computing, and novel interpretability methods show great potential in overcoming these challenges and bridging the gap towards precision outcome modeling in radiotherapy. Examples of these promising technologies will be presented and their potential role in improving outcome modeling will be discussed.

DQAgui: a graphical user interface for the MIRACUM data quality assessment tool

Background

With the growing impact of observational research studies, there is also a growing focus on data quality (DQ). As opposed to experimental study designs, observational research studies are performed using data mostly collected in a non-research context (secondary use). Depending on the number of data elements to be analyzed, DQ reports of data stored within research networks can grow very large. They might be cumbersome to read and important information could be overseen quickly. To address this issue, a DQ assessment (DQA) tool with a graphical user interface (GUI) was developed and provided as a web application.

Methods

The aim was to provide an easy-to-use interface for users without prior programming knowledge to carry out DQ checks and to present the results in a clearly structured way. This interface serves as a starting point for a more detailed investigation of possible DQ irregularities. A user-centered development process ensured the practical feasibility of the interactive GUI. The interface was implemented in the R programming language and aligned to Kahn et al.’s DQ categories conformance, completeness and plausibility.

Results

With DQAgui, an R package with a web-app frontend for DQ assessment was developed. The GUI allows users to perform DQ analyses of tabular data sets and to systematically evaluate the results. During the development of the GUI, additional features were implemented, such as analyzing a subset of the data by defining time periods and restricting the analyses to certain data elements.

Conclusions

As part of the MIRACUM project, DQAgui is now being used at ten German university hospitals for DQ assessment and to provide a central overview of the availability of important data elements in a datamap over 2 years. Future development efforts should focus on design optimization and include a usability evaluation.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01961-z.