Bringing Precision Medicine into the Clinical Practice: The Role of Explainable Artificial Intelligence and Interpretable Models

A special issue of Bioengineering (ISSN 2306-5354). This special issue belongs to the section "Biomedical Engineering and Biomaterials".

Deadline for manuscript submissions: 31 May 2025 | Viewed by 1076

Special Issue Editors


E-Mail Website
Guest Editor
Department of Electrical and Information Engineering, Polytechnic of Bari, 70126 Bari, BA, Italy
Interests: medical image analysis; deep learning; radiomics; pathomics; clinical decision support; explainable artificial intelligence
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Electrical and Information Engineering, Polytechnic of Bari, 70126 Bari, BA, Italy
Interests: biomedical engineering; bioengineering; medical image processing; clinical translation

Special Issue Information

Dear Colleagues,

Precision Medicine paves the way to tailor disease prevention and treatment in a specialized manner for each patient, leveraging on high-throughput patient data, encompassing clinical, imaging, and multi-omics features, among the others. Artificial Intelligence (AI) techniques have a huge impact on the handling of this incredible quantity and variety of data for predicting diagnosis, prognosis, or treatment. Nevertheless, Clinical Decision Support Systems (CDSS) based on AI are difficult to implement in the clinical routine, since AI systems are seen as black boxes by both physicians and patients. To further complicate this issue, the latest developments of CDSS do not concern single-type data analysis but involve multimodal fusion from multiple sources with a high heterogeneity. Interpretable Models, such as decision trees and linear regressors or classifiers, whose decisions can be easily understood by the stakeholders involved, are often too simple to effectively handle intricate medical data analysis tasks. Nevertheless, efforts in Feature Reduction techniques can help in individuating a small subset of relevant characteristics that can act as a simplified diagnostic, prognostic, or therapeutic signature. In recent years, Explainable Artificial Intelligence (XAI) has established as a fundamental theme in the research involving applications of AI in medicine, offering the possibility to unveil the mechanisms behind the decision-making process of those complex automated systems. Furthermore, novel applications of XAI are emerging, as those related to provide time-dependent explanations for survival models, enabling new frontiers of analysis to the practitioners. Hence, this special issue investigates the potential offered by XAI and Interpretable Models in enabling the adoption of Precision Medicine into clinical practice. Methodological articles concerning algorithmic developments, as well as impactful applications that leverage on existing methods, can be submitted to this Special Issue. Research areas may include (but are not limited to) the following:

- Explainable CDSS
- XAI for Medical Imaging
- Clinical Translation through XAI
- Time-dependent XAI
- Multimodal Data Analysis
- Interpretable Models
- Feature Reduction
- Radiomics
- Pathomics
- Bioinformatics

We look forward to receiving your contributions.

Dr. Nicola Altini
Dr. Gian Maria Zaccaria
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Bioengineering is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • precision medicine
  • clinical practice
  • explainable artificial intelligence
  • interpretable models

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

14 pages, 2131 KiB  
Article
Bringing Precision to Pediatric Care: Explainable AI in Predicting No-Show Trends Before and During the COVID-19 Pandemic
by Quincy A. Hathaway, Naveena Yanamala, TaraChandra Narumanchi and Janani Narumanchi
Bioengineering 2025, 12(3), 227; https://doi.org/10.3390/bioengineering12030227 - 24 Feb 2025
Viewed by 674
Abstract
Patient no-shows significantly disrupt pediatric healthcare delivery, highlighting the necessity for precise predictive models, especially during the dynamic shifts caused by the SARS-CoV-2 pandemic. In outpatient settings, these no-shows result in medical resource underutilization, increased healthcare costs, reduced access to care, and decreased [...] Read more.
Patient no-shows significantly disrupt pediatric healthcare delivery, highlighting the necessity for precise predictive models, especially during the dynamic shifts caused by the SARS-CoV-2 pandemic. In outpatient settings, these no-shows result in medical resource underutilization, increased healthcare costs, reduced access to care, and decreased clinic efficiency and increased provider workload. The objective is to develop a predictive model for patient no-shows using data-driven techniques. We analyzed five years of historical data retrieved from both a scheduling system and electronic health records from a general pediatrics clinic within the WVU Health systems. This dataset includes 209,408 visits from 2015 to 2018, 82,925 visits in 2019, and 58,820 visits in 2020, spanning both the pre-pandemic and pandemic periods. The data include variables such as patient demographics, appointment details, timing, hospital characteristics, appointment types, and environmental factors. Our XGBoost model demonstrated robust predictive capabilities, notably outperforming traditional “no-show rate” metrics. Precision and recall metrics for all features were 0.82 and 0.88, respectively. Receiver Operator Characteristic (ROC) analysis yielded AUCs of 0.90 for all features and 0.88 for the top five predictors when evaluated on the 2019 cohort. Furthermore, model generalization across racial/ethnic groups was also observed. Evaluation on 2020 telehealth data reaffirmed model efficacy (AUC: 0.90), with consistent top predictive features. Our study presents a sophisticated predictive model for pediatric no-show rates, offering insights into nuanced factors influencing attendance behavior. The model’s adaptability to evolving healthcare delivery models, including telehealth, underscores its potential for enhancing clinical practice and resource allocation. Full article
Show Figures

Figure 1

Back to TopTop