Submit to Diagnostics Review for Diagnostics Propose a Special Issue

Journal Browser

Improving Diagnosis in Medicine: The Interplay between Physicians and Clinical Decision Support Systems

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: closed (30 November 2021) | Viewed by 11862

Share This Special Issue

Special Issue Editor

Prof. Dr. Taro Shimizu

E-Mail
Guest Editor

Diagnostic and Generalist Medicine, Dokkyo Medical University Graduate School of Medicine, Tochigi 321-0293, Japan
Interests: diagnostic strategy; clinical reasoning; diagnostic error; medical education

Special Issue Information

Dear Colleagues,

Improving diagnosis has become a global topic that needs to be focused on. The focus of improving diagnostic errors has broadened from the consideration of the physician's brain, or more precisely, the physician's ability to make decisions in clinical diagnosis, to situativity. Situativity is a set of theories based on cognitive psychology that broadly capture the factors that influence the thinking and learning of medical professionals, e.g., physicians, in terms of the social and complex nature of cognition. It is hoped that research in this area will provide an opportunity to reconstruct ways of understanding cognitive processes and thus gain new approaches to address diagnostic errors. As multiple and various strategies are developed over time to improve diagnosis, the role that the clinical decision support systems (CDSS) have played in diagnosis, and will play in the future, is significant. In general, CDSS have been described as systems that support clinicians in making health choices by linking observation and knowledge of patients' health conditions. There are clinical and technical challenges in the collaboration between humans and CDSS in diagnosis. For example, CDSS need to rely on humans to input raw data, such as medical history and physical findings, the diversity and complexity of real clinical workflows, as well as ethical issues. On the other hand, if these challenges can be overcome, we can expect the better augmentation of CDSS with humans, which will not only have clinical benefits in ensuring a certain level of quality in diagnosis, but also in improving the quality of care for patients. The successful application of the CDSS is expected to provide clinical benefits, in terms of ensuring a certain level of diagnostic quality, as well as educational benefits, in terms of providing educational feedback to clinicians through the CDSS intervention. This will lead to better health outcomes for patients.

In this Special Issue, we report on the benefits and challenges of CDSS working with human diagnostic thinking and identify prospects for extensions between the two systems in the era of situativity.

Prof. Dr. Taro Shimizu
Guest Editor

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. Diagnostics is an international peer-reviewed open access semimonthly 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 2600 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

Diagnostic error
Diagnostic strategy
Clinical reasoning
Clinical decision support system
Artificial intelligence
Medical education
Situativity

Published Papers (5 papers)

Download All Papers

Research

Jump to: Other

23 pages, 3875 KiB

Open AccessArticle

Interpretable Clinical Decision Support System for Audiology Based on Predicted Common Audiological Functional Parameters (CAFPAs)

by Mareike Buhl

Diagnostics 2022, 12(2), 463; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12020463 - 11 Feb 2022

Cited by 3 | Viewed by 1467

Abstract

Common Audiological Functional Parameters (CAFPAs) were previously introduced as abstract, measurement-independent representation of audiological knowledge, and expert-estimated CAFPAs were shown to be applicable as an interpretable intermediate layer in a clinical decision support system (CDSS). Prediction models for CAFPAs were built based on expert knowledge and one audiological database to allow for data-driven estimation of CAFPAs for new, individual patients for whom no expert-estimated CAFPAs are available. Based on the combination of these components, the current study explores the feasibility of constructing a CDSS which is as interpretable as expert knowledge-based classification and as data-driven as machine learning-based classification. To test this hypothesis, the current study investigated the equivalence in performance of predicted CAFPAs compared to expert-estimated CAFPAs in an audiological classification task, analyzed the importance of different CAFPAs for high and comparable performance, and derived explanations for differences in classified categories. Results show that the combination of predicted CAFPAs and statistical classification enables to build an interpretable but data-driven CDSS. The classification provides good accuracy, with most categories being correctly classified, while some confusions can be explained by the properties of the employed database. This could be improved by including additional databases in the CDSS, which is possible within the presented framework. Full article

(This article belongs to the Special Issue Improving Diagnosis in Medicine: The Interplay between Physicians and Clinical Decision Support Systems)

► Show Figures

Figure 1

13 pages, 1656 KiB

Open AccessArticle

A Machine Learning Model for Predicting Unscheduled 72 h Return Visits to the Emergency Department by Patients with Abdominal Pain

by Chun-Chuan Hsu, Cheng-C.J. Chu, Ching-Heng Lin, Chien-Hsiung Huang, Chip-Jin Ng, Guan-Yu Lin, Meng-Jiun Chiou, Hsiang-Yun Lo and Shou-Yen Chen

Diagnostics 2022, 12(1), 82; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12010082 - 30 Dec 2021

Cited by 5 | Viewed by 1989

Abstract

Seventy-two-hour unscheduled return visits (URVs) by emergency department patients are a key clinical index for evaluating the quality of care in emergency departments (EDs). This study aimed to develop a machine learning model to predict 72 h URVs for ED patients with abdominal pain. Electronic health records data were collected from the Chang Gung Research Database (CGRD) for 25,151 ED visits by patients with abdominal pain and a total of 617 features were used for analysis. We used supervised machine learning models, namely logistic regression (LR), support vector machine (SVM), random forest (RF), extreme gradient boosting (XGB), and voting classifier (VC), to predict URVs. The VC model achieved more favorable overall performance than other models (AUROC: 0.74; 95% confidence interval (CI), 0.69–0.76; sensitivity, 0.39; specificity, 0.89; F1 score, 0.25). The reduced VC model achieved comparable performance (AUROC: 0.72; 95% CI, 0.69–0.74) to the full models using all clinical features. The VC model exhibited the most favorable performance in predicting 72 h URVs for patients with abdominal pain, both for all-features and reduced-features models. Application of the VC model in the clinical setting after validation may help physicians to make accurate decisions and decrease URVs. Full article

(This article belongs to the Special Issue Improving Diagnosis in Medicine: The Interplay between Physicians and Clinical Decision Support Systems)

► Show Figures

Figure 1

12 pages, 1707 KiB

Open AccessArticle

Characterization of the Diagnostic Performance of a Novel COVID-19 PETIA in Comparison to Four Routine N-, S- and RBD-Antigen Based Immunoassays

by Alexander Spaeth, Thomas Masetto, Jessica Brehm, Leoni Wey, Christian Kochem, Martin Brehm, Christoph Peter and Matthias Grimmler

Diagnostics 2021, 11(8), 1332; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11081332 - 25 Jul 2021

Cited by 4 | Viewed by 2246

Abstract

In 2019, a novel coronavirus emerged in Wuhan in the province of Hubei, China. The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) quickly spread across the globe, causing the neoteric COVID-19 pandemic. SARS-CoV-2 is commonly transmitted by droplet infection and aerosols when coughing or sneezing, as well as high-risk exposures to infected individuals by face-to-face contact without protective gear. To date, a broad variety of techniques have emerged to assess and quantify the specific antibody response of a patient towards a SARS-CoV-2 infection. Here, we report the first comprehensive comparison of five different assay systems: Enzyme-Linked Immunosorbent Assay (ELISA), Chemiluminescence Immunoassay (CLIA), Electro-Chemiluminescence Immunoassay (ECLIA), and a new Particle-Enhanced Turbidimetric Immunoassay (PETIA) for SARS-CoV-2. Furthermore, we also evaluated the suitability of N-, S1- and RBD-antigens for quantifying the SARS-CoV-2 specific immune response. Linearity and precision, overall sensitivity and specificity of the assays, stability of samples, and cross-reactivity of general viral responses, as well as common coronaviruses, were assessed. Moreover, the reactivity of all tests to seroconversion and different sample matrices was quantified. All five assays showed good overall agreement, with 76% and 87% similarity for negative and positive samples, respectively. In conclusion, all evaluated methods showed a high consistency of results and suitability for the robust quantification of the SARS-CoV-2-derived immune response. Full article

(This article belongs to the Special Issue Improving Diagnosis in Medicine: The Interplay between Physicians and Clinical Decision Support Systems)

► Show Figures

Figure 1

12 pages, 1027 KiB

Open AccessArticle

Evaluating of Red Blood Cell Distribution Width, Comorbidities and Electrocardiographic Ratios as Predictors of Prognosis in Patients with Pulmonary Hypertension

by Mario E. Baltazares-Lipp, Alberto Aguilera-Velasco, Arnoldo Aquino-Gálvez, Rafael Velázquez-Cruz, Rafael J. Hernández-Zenteno, Noé Alvarado-Vásquez, Angel Camarena, M. Patricia Sierra-Vargas, Juan L. Chávez-Pacheco, Víctor Ruiz, Citlaltepetl Salinas-Lara, Martha L. Tena-Suck, Yair Romero, Luz M. Torres-Espíndola and Manuel Castillejos-López

Diagnostics 2021, 11(7), 1297; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics11071297 - 20 Jul 2021

Cited by 3 | Viewed by 2385

Abstract

Pulmonary hypertension is a rare condition that impairs patients’ quality of life and life expectancy. The development of noninvasive instruments may help elucidate the prognosis of this cardiorespiratory disease. We aimed to evaluate the utility of routinely performed noninvasive test results as prognostic markers in patients with pulmonary hypertension. We enrolled 198 patients with mean pulmonary artery pressure >25 mmHg measured at cardiac catheterisation or echocardiographic pulmonary artery systolic pressure > 40 mmHg and tricuspid regurgitation Vmax >2.9 m/s, and clinical information regarding management and follow-up studies from the date of diagnosis. Multivariate analysis revealed that female sex [HR: 0.21, (95% CI: 0.07–0.64); p = 0.006], the presence of collagenopathies [HR: 8.63, (95% CI: 2.38–31.32); p = 0.001], an increased red blood cell distribution width [HR: 1.25, (95% CI: 1.04–1.49); p = 0.017] and an increased electrocardiographic P axis (P°)/T axis (T°) ratio [HR: 0.93, (95% CI: 0.88–0.98); p = 0.009] were severity-associated factors, while older age [HR: 1.57, (95% CI: 1.04–1.28); p = 0.006], an increased QRS axis (QRS°)/T° ratio [HR: 1.21, (95% CI: 1.09–1.34); p < 0.001], forced expiratory volume in 1 s [HR: 0.94, (95% CI: 0.91–0.98); p = 0.01] and haematocrit [HR: 0.93, (95% CI: 0.87–0.99); p = 0.04] were mortality-associated factors. Our results support the importance of red blood cell distribution width, electrocardiographic ratios and collagenopathies for assessing pulmonary hypertension prognosis. Full article

(This article belongs to the Special Issue Improving Diagnosis in Medicine: The Interplay between Physicians and Clinical Decision Support Systems)

► Show Figures

Figure 1

Other

Jump to: Research

9 pages, 575 KiB

Open AccessPerspective

System 2 Diagnostic Process for the Next Generation of Physicians: “Inside” and “Outside” Brain—The Interplay between Human and Machine

by Taro Shimizu

Diagnostics 2022, 12(2), 356; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics12020356 - 30 Jan 2022

Cited by 3 | Viewed by 2840

Abstract

Improving diagnosis has been one of the most critical issues in medicine for the last two decades. In the context of the rise of digital health and its augmentation and human diagnostic thinking, it has become necessary to integrate the concept of digital diagnosis into dual-process theory (DPT), which is the fundamental axis of the diagnostic thinking process physicians. Particularly, since the clinical decision support system (CDSS) corresponds to analytical thinking (system 2) in DPT, it is necessary to redefine system 2 to include the CDSS. However, to the best of my knowledge there has been no concrete conceptual model based on this need. The innovation and novelty of this paper are that it redefines system 2 to include new concepts and shows the relationship among the breakdown of system 2. In this definition, system 2 is divided into “inside” and “outside” brains, where “inside” includes symptomatologic, anatomical, biomechanical–physiological, and etiological thinking approaches, and “outside” includes CDSS. Moreover, this paper discusses the actual and possible future interplay between “inside” and “outside.” The author envisions that this paper will serve as a cornerstone for the future development of system 2 diagnostic thinking strategy. Full article

(This article belongs to the Special Issue Improving Diagnosis in Medicine: The Interplay between Physicians and Clinical Decision Support Systems)

► Show Figures