1
|
Zhao Z, Zhu J, Jiao P, Wang J, Zhang X, Lu X, Zhang Y. Hybrid-FHR: a multi-modal AI approach for automated fetal acidosis diagnosis. BMC Med Inform Decis Mak 2024; 24:19. [PMID: 38247009 PMCID: PMC10801938 DOI: 10.1186/s12911-024-02423-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2023] [Accepted: 01/10/2024] [Indexed: 01/23/2024] Open
Abstract
BACKGROUND In clinical medicine, fetal heart rate (FHR) monitoring using cardiotocography (CTG) is one of the most commonly used methods for assessing fetal acidosis. However, as the visual interpretation of CTG depends on the subjective judgment of the clinician, this has led to high inter-observer and intra-observer variability, making it necessary to introduce automated diagnostic techniques. METHODS In this study, we propose a computer-aided diagnostic algorithm (Hybrid-FHR) for fetal acidosis to assist physicians in making objective decisions and taking timely interventions. Hybrid-FHR uses multi-modal features, including one-dimensional FHR signals and three types of expert features designed based on prior knowledge (morphological time domain, frequency domain, and nonlinear). To extract the spatiotemporal feature representation of one-dimensional FHR signals, we designed a multi-scale squeeze and excitation temporal convolutional network (SE-TCN) backbone model based on dilated causal convolution, which can effectively capture the long-term dependence of FHR signals by expanding the receptive field of each layer's convolution kernel while maintaining a relatively small parameter size. In addition, we proposed a cross-modal feature fusion (CMFF) method that uses multi-head attention mechanisms to explore the relationships between different modalities, obtaining more informative feature representations and improving diagnostic accuracy. RESULTS Our ablation experiments show that the Hybrid-FHR outperforms traditional previous methods, with average accuracy, specificity, sensitivity, precision, and F1 score of 96.8, 97.5, 96, 97.5, and 96.7%, respectively. CONCLUSIONS Our algorithm enables automated CTG analysis, assisting healthcare professionals in the early identification of fetal acidosis and the prompt implementation of interventions.
Collapse
Affiliation(s)
- Zhidong Zhao
- School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China.
| | - Jiawei Zhu
- College of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, China
| | - Pengfei Jiao
- School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China
| | - Jinpeng Wang
- School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China
| | - Xiaohong Zhang
- College of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, China
| | - Xinmiao Lu
- College of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou, China
| | - Yefei Zhang
- School of Cyberspace, Hangzhou Dianzi University, Hangzhou, China
| |
Collapse
|
2
|
Mendis L, Palaniswami M, Brownfoot F, Keenan E. Computerised Cardiotocography Analysis for the Automated Detection of Fetal Compromise during Labour: A Review. Bioengineering (Basel) 2023; 10:1007. [PMID: 37760109 PMCID: PMC10525263 DOI: 10.3390/bioengineering10091007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Revised: 08/17/2023] [Accepted: 08/22/2023] [Indexed: 09/29/2023] Open
Abstract
The measurement and analysis of fetal heart rate (FHR) and uterine contraction (UC) patterns, known as cardiotocography (CTG), is a key technology for detecting fetal compromise during labour. This technology is commonly used by clinicians to make decisions on the mode of delivery to minimise adverse outcomes. A range of computerised CTG analysis techniques have been proposed to overcome the limitations of manual clinician interpretation. While these automated techniques can potentially improve patient outcomes, their adoption into clinical practice remains limited. This review provides an overview of current FHR and UC monitoring technologies, public and private CTG datasets, pre-processing steps, and classification algorithms used in automated approaches for fetal compromise detection. It aims to highlight challenges inhibiting the translation of automated CTG analysis methods from research to clinical application and provide recommendations to overcome them.
Collapse
Affiliation(s)
- Lochana Mendis
- Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, VIC 3010, Australia; (M.P.); (E.K.)
| | - Marimuthu Palaniswami
- Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, VIC 3010, Australia; (M.P.); (E.K.)
| | - Fiona Brownfoot
- Obstetric Diagnostics and Therapeutics Group, Department of Obstetrics and Gynaecology, The University of Melbourne, Heidelberg, VIC 3084, Australia;
| | - Emerson Keenan
- Department of Electrical and Electronic Engineering, The University of Melbourne, Parkville, VIC 3010, Australia; (M.P.); (E.K.)
- Obstetric Diagnostics and Therapeutics Group, Department of Obstetrics and Gynaecology, The University of Melbourne, Heidelberg, VIC 3084, Australia;
| |
Collapse
|
3
|
Ribeiro M, Nunes I, Castro L, Costa-Santos C, S. Henriques T. Machine learning models based on clinical indices and cardiotocographic features for discriminating asphyxia fetuses—Porto retrospective intrapartum study. Front Public Health 2023; 11:1099263. [PMID: 37033082 PMCID: PMC10074982 DOI: 10.3389/fpubh.2023.1099263] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2022] [Accepted: 02/20/2023] [Indexed: 03/22/2023] Open
Abstract
IntroductionPerinatal asphyxia is one of the most frequent causes of neonatal mortality, affecting approximately four million newborns worldwide each year and causing the death of one million individuals. One of the main reasons for these high incidences is the lack of consensual methods of early diagnosis for this pathology. Estimating risk-appropriate health care for mother and baby is essential for increasing the quality of the health care system. Thus, it is necessary to investigate models that improve the prediction of perinatal asphyxia. Access to the cardiotocographic signals (CTGs) in conjunction with various clinical parameters can be crucial for the development of a successful model.ObjectivesThis exploratory work aims to develop predictive models of perinatal asphyxia based on clinical parameters and fetal heart rate (fHR) indices.MethodsSingle gestations data from a retrospective unicentric study from Centro Hospitalar e Universitário do Porto de São João (CHUSJ) between 2010 and 2018 was probed. The CTGs were acquired and analyzed by Omniview-SisPorto, estimating several fHR features. The clinical variables were obtained from the electronic clinical records stored by ObsCare. Entropy and compression characterized the complexity of the fHR time series. These variables' contribution to the prediction of asphyxia perinatal was probed by binary logistic regression (BLR) and Naive-Bayes (NB) models.ResultsThe data consisted of 517 cases, with 15 pathological cases. The asphyxia prediction models showed promising results, with an area under the receiver operator characteristic curve (AUC) >70%. In NB approaches, the best models combined clinical and SisPorto features. The best model was the univariate BLR with the variable compression ratio scale 2 (CR2) and an AUC of 94.93% [94.55; 95.31%].ConclusionBoth BLR and Bayesian models have advantages and disadvantages. The model with the best performance predicting perinatal asphyxia was the univariate BLR with the CR2 variable, demonstrating the importance of non-linear indices in perinatal asphyxia detection. Future studies should explore decision support systems to detect sepsis, including clinical and CTGs features (linear and non-linear).
Collapse
Affiliation(s)
- Maria Ribeiro
- Institute for Systems and Computer Engineering, Technology and Science (INESC-TEC), Porto, Portugal
- Computer Science Department, Faculty of Sciences, University of Porto, Porto, Portugal
- *Correspondence: Maria Ribeiro
| | - Inês Nunes
- Institute of Biomedical Sciences Abel Salazar, University of Porto, Porto, Portugal
- Centro Materno-Infantil do Norte—Centro Hospitalar e Universitário do Porto, Porto, Portugal
- Centre for Health Technology and Services Research (CINTESIS), Faculty of Medicine University of Porto, Porto, Portugal
| | - Luísa Castro
- CINTESIS@RISE, MEDCIDS, Faculty of Medicine, University of Porto, Porto, Portugal
- School of Health of Polytechnic of Porto, Porto, Portugal
| | | | - Teresa S. Henriques
- CINTESIS@RISE, MEDCIDS, Faculty of Medicine, University of Porto, Porto, Portugal
| |
Collapse
|
4
|
Silva S, Ribeiro F, Figueira V, Pinho F. Methodological Considerations in the Kinematic and Kinetic Analysis of Human Movement among Healthy Adolescents: A Scoping Review of Nonlinear Measures in Data Processing. SENSORS (BASEL, SWITZERLAND) 2022; 23:304. [PMID: 36616902 PMCID: PMC9823368 DOI: 10.3390/s23010304] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Revised: 12/22/2022] [Accepted: 12/24/2022] [Indexed: 06/17/2023]
Abstract
Nonlinear measures have increasingly revealed the quality of human movement and its behaviour over time. Further analyses of human movement in real contexts are crucial for understanding its complex dynamics. The main objective was to identify and summarize the nonlinear measures used in data processing during out-of-laboratory assessments of human movement among healthy adolescents. Summarizing the methodological considerations was the secondary objective. The inclusion criteria were as follows: According to the Population, Concept, and Context (PCC) framework, healthy teenagers between 10 and 19 years old that reported kinetic and/or kinematic nonlinear data-processing measurements related to human movement in non-laboratory settings were included. PRISMA-ScR was used to conduct this review. PubMed, Science Direct, the Web of Science, and Google Scholar were searched. Studies published between the inception of the database and March 2022 were included. In total, 10 of the 2572 articles met the criteria. The nonlinear measures identified included entropy (n = 8), fractal analysis (n = 3), recurrence quantification (n = 2), and the Lyapunov exponent (n = 2). In addition to walking (n = 4) and swimming (n = 2), each of the remaining studies focused on different motor tasks. Entropy measures are preferred when studying the complexity of human movement, especially multiscale entropy, with authors also carefully combining different measures, namely entropy and fractal analysis.
Collapse
Affiliation(s)
- Sandra Silva
- Escola Superior de Saúde do Vale do Ave, Cooperativa de Ensino Superior Politécnico e Universitário, Rua José António Vidal, 81, 4760-409 Vila Nova de Famalicão, Portugal
- School of Health Sciences, University of Aveiro, 3810-193 Aveiro, Portugal
- Department of Medical Sciences, University of Aveiro, 3810-193 Aveiro, Portugal
| | - Fernando Ribeiro
- School of Health Sciences, University of Aveiro, 3810-193 Aveiro, Portugal
- Institute of Biomedicine—iBiMED, University of Aveiro, 3810-193 Aveiro, Portugal
| | - Vânia Figueira
- Escola Superior de Saúde do Vale do Ave, Cooperativa de Ensino Superior Politécnico e Universitário, Rua José António Vidal, 81, 4760-409 Vila Nova de Famalicão, Portugal
- Research Centre in Physical Activity, Health and Leisure, Faculty of Sport, University of Porto, Rua Dr. Plácido da Costa, 91, 4200-450 Porto, Portugal
| | - Francisco Pinho
- Escola Superior de Saúde do Vale do Ave, Cooperativa de Ensino Superior Politécnico e Universitário, Rua José António Vidal, 81, 4760-409 Vila Nova de Famalicão, Portugal
| |
Collapse
|
5
|
Ben M'Barek I, Jauvion G, Ceccaldi P. Computerized cardiotocography analysis during labor - A state-of-the-art review. Acta Obstet Gynecol Scand 2022; 102:130-137. [PMID: 36541016 PMCID: PMC9889319 DOI: 10.1111/aogs.14498] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Revised: 12/01/2022] [Accepted: 12/02/2022] [Indexed: 12/24/2022]
Abstract
Cardiotocography is defined as the recording of fetal heart rate and uterine contractions and is widely used during labor as a screening tool to determine fetal wellbeing. The visual interpretation of the cardiotocography signals by the practitioners, following common guidelines, is subject to a high interobserver variability, and the efficiency of cardiotocography monitoring is still debated. Since the 1990s, researchers and practitioners work on designing reliable computer-aided systems to assist practitioners in cardiotocography interpretation during labor. Several systems are integrated in the monitoring devices, mostly based on the guidelines, but they have not clearly demonstrated yet their usefulness. In the last decade, the availability of large clinical databases as well as the emergence of machine learning and deep learning methods in healthcare has led to a surge of studies applying those methods to cardiotocography signals analysis. The state-of-the-art systems perform well to detect fetal hypoxia when evaluated on retrospective cohorts, but several challenges remain to be tackled before they can be used in clinical practice. First, the development and sharing of large, open and anonymized multicentric databases of perinatal and cardiotocography data during labor is required to build more accurate systems. Also, the systems must produce interpretable indicators along with the prediction of the risk of fetal hypoxia in order to be appropriated and trusted by practitioners. Finally, common standards should be built and agreed on to evaluate and compare those systems on retrospective cohorts and to validate their use in clinical practice.
Collapse
Affiliation(s)
- Imane Ben M'Barek
- Department of Obstetrics and GynecologyAssistance Publique Hôpitaux de Paris – Hôpital BeaujonClichy La GarenneFrance,Université Paris CitéParisFrance,Health Simulation Department, iLumensUniversité Paris CitéParisFrance
| | | | - Pierre‐François Ceccaldi
- Université Paris CitéParisFrance,Health Simulation Department, iLumensUniversité Paris CitéParisFrance,Department of Gynecology‐Obstetrics and Reproductive MedicineHôpital FochSuresnesFrance
| |
Collapse
|
6
|
Arantes FS, Rosa Oliveira V, Leão AKM, Afonso JPR, Fonseca AL, Fonseca DRP, Mello DACPG, Costa IP, Oliveira LVF, da Palma RK. Heart rate variability: A biomarker of frailty in older adults? Front Med (Lausanne) 2022; 9:1008970. [PMID: 36314012 PMCID: PMC9614264 DOI: 10.3389/fmed.2022.1008970] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 09/26/2022] [Indexed: 11/13/2022] Open
Abstract
Frailty is a state of critical loss of physiological complexity resulting in greater vulnerability to stressors and has been characterized as a debility syndrome in the older adult. Changes in functional capacity and the cardiovascular system during aging are the most significant and relevant for this population, including the clinically healthy. In this sense, this review aims to investigate methods to monitor the performance of older adults, such as heart rate variability and verify how it can be related to frailty. It contributes to understanding that the changes in heart variability can be a marker for frailty in older adults.
Collapse
Affiliation(s)
- Flávia Sousa Arantes
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil
| | - Vinicius Rosa Oliveira
- Research Group on Methodology, Methods, Models and Outcomes of Health and Social Sciences (M3O), Faculty of Health Sciences and Welfare, Center for Health and Social Care Research (CESS), University of Vic-Central University of Catalonia (UVic-UCC), Vic, Spain
| | - Aime Karla Moraes Leão
- Department of Research, Innovation and Postgraduate, University of Rio Verde, Rio Verde, Brazil
| | - João Pedro Ribeiro Afonso
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil
| | - Adriano Luis Fonseca
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil
| | - Daniela Rosana Pedro Fonseca
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil
| | - Diego Antonio C. Pina Gomes Mello
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil
| | - Ivan Peres Costa
- Rehabilitation Sciences, University Nove de Julho (UNINOVE), São Paulo, Brazil,FacPhysio, São Paulo, Brazil
| | - Luiz Vicente Franco Oliveira
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil
| | - Renata Kelly da Palma
- Human Movement and Rehabilitation, Post-Graduate Program Medical School, Evangelic University of Goiás-UniEVANGÉLICA, Anápolis, Brazil,Department of Surgery, School of Veterinary Medicine and Animal Sciences, University of São Paulo, São Paulo, Brazil,Facultad de Ciencias de la Salud de Manresa, Universitat de Vic-Universitat Central de Catalunya (UVic-UCC), Manresa, Spain,*Correspondence: Renata Kelly da Palma
| |
Collapse
|
7
|
Spairani E, Daniele B, Signorini MG, Magenes G. A deep learning mixed-data type approach for the classification of FHR signals. Front Bioeng Biotechnol 2022; 10:887549. [PMID: 36003538 PMCID: PMC9393210 DOI: 10.3389/fbioe.2022.887549] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Accepted: 07/01/2022] [Indexed: 11/21/2022] Open
Abstract
The Cardiotocography (CTG) is a widely diffused monitoring practice, used in Ob-Gyn Clinic to assess the fetal well-being through the analysis of the Fetal Heart Rate (FHR) and the Uterine contraction signals. Due to the complex dynamics regulating the Fetal Heart Rate, a reliable visual interpretation of the signal is almost impossible and results in significant subjective inter and intra-observer variability. Also, the introduction of few parameters obtained from computer analysis did not solve the problem of a robust antenatal diagnosis. Hence, during the last decade, computer aided diagnosis systems, based on artificial intelligence (AI) machine learning techniques have been developed to assist medical decisions. The present work proposes a hybrid approach based on a neural architecture that receives heterogeneous data in input (a set of quantitative parameters and images) for classifying healthy and pathological fetuses. The quantitative regressors, which are known to represent different aspects of the correct development of the fetus, and thus are related to the fetal healthy status, are combined with features implicitly extracted from various representations of the FHR signal (images), in order to improve the classification performance. This is achieved by setting a neural model with two connected branches, consisting respectively of a Multi-Layer Perceptron (MLP) and a Convolutional Neural Network (CNN). The neural architecture was trained on a huge and balanced set of clinical data (14.000 CTG tracings, 7000 healthy and 7000 pathological) recorded during ambulatory non stress tests at the University Hospital Federico II, Napoli, Italy. After hyperparameters tuning and training, the neural network proposed has reached an overall accuracy of 80.1%, which is a promising result, as it has been obtained on a huge dataset.
Collapse
Affiliation(s)
- Edoardo Spairani
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Beniamino Daniele
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico Milano, Milano, Italy
| | | | - Giovanni Magenes
- Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
- *Correspondence: Giovanni Magenes,
| |
Collapse
|