1
|
Homma Y, Zhuang X, Watari T, Hayashi K, Baba T, Kamath A, Ishijima M. Differences in acoustic parameters of hammering sounds between successful and unsuccessful initial cementless cup press-fit fixation in total hip arthroplasty. Bone Jt Open 2024; 5:154-161. [PMID: 38423101 PMCID: PMC10904203 DOI: 10.1302/2633-1462.53.bjo-2023-0160.r1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/02/2024] Open
Abstract
Aims It is important to analyze objectively the hammering sound in cup press-fit technique in total hip arthroplasty (THA) in order to better understand the change of the sound during impaction. We hypothesized that a specific characteristic would present in a hammering sound with successful fixation. We designed the study to quantitatively investigate the acoustic characteristics during cementless cup impaction in THA. Methods In 52 THAs performed between November 2018 and April 2022, the acoustic parameters of the hammering sound of 224 impacts of successful press-fit fixation, and 55 impacts of unsuccessful press-fit fixation, were analyzed. The successful fixation was defined if the following two criteria were met: 1) intraoperatively, the stability of the cup was retained after manual application of the torque test; and 2) at one month postoperatively, the cup showed no translation on radiograph. Each hammering sound was converted to sound pressures in 24 frequency bands by fast Fourier transform analysis. Basic patient characteristics were assessed as potential contributors to the hammering sound. Results The median sound pressure (SP) of successful fixation at 0.5 to 1.0 kHz was higher than that of unsuccessful fixation (0.0694 (interquartile range (IQR) 0.04721 to 0.09576) vs 0.05425 (IQR 0.03047 to 0.06803), p < 0.001). The median SP of successful fixation at 3.5 to 4.0 kHz and 4.0 to 4.5 kHz was lower than that of unsuccessful fixation (0.0812 (IQR 0.05631 to 0.01161) vs 0.1233 (IQR 0.0730 to 0.1449), p < 0.001; and 0.0891 (IQR 0.0526 to 0.0891) vs 0.0885 (IQR 0.0716 to 0.1048); p < 0.001, respectively). There was a statistically significant positive relationship between body weight and SP at 0.5 to 1.0 kHz (p < 0.001). Multivariate analyses indicated that the SP at 0.5 to 1.0 kHz and 3.5 to 4.0 kHz was independently associated with the successful fixation. Conclusion The frequency bands of 0.5 to 1.0 and 3.5 to 4.0 kHz were the key to distinguish the sound characteristics between successful and unsuccessful press-fit cup fixation.
Collapse
Affiliation(s)
- Yasuhiro Homma
- Department of Medicine for Orthopaedics and Motor Organ, Juntendo University Graduate School of Medicine, Tokyo, Japan
- Department of Orthopaedics, Faculty of Medicine, Juntendo University, Tokyo, Japan
- Department of Community Medicine and Research for Bone and Joint Diseases, Juntendo University Graduate School of Medicine, Tokyo, Japan
| | - Xu Zhuang
- Department of Medicine for Orthopaedics and Motor Organ, Juntendo University Graduate School of Medicine, Tokyo, Japan
| | - Taiji Watari
- Department of Medicine for Orthopaedics and Motor Organ, Juntendo University Graduate School of Medicine, Tokyo, Japan
- Department of Orthopaedics, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Koju Hayashi
- Department of Orthopaedics, Faculty of Medicine, Juntendo University, Tokyo, Japan
| | - Tomonori Baba
- Department of Medicine for Orthopaedics and Motor Organ, Juntendo University Graduate School of Medicine, Tokyo, Japan
- Department of Orthopaedics, Faculty of Medicine, Juntendo University, Tokyo, Japan
- Department of Pathophysiology for Locomotive Diseases, Juntendo University Graduate School of Medicine, Tokyo, Japan
| | - Atul Kamath
- Department of Orthopaedic Surgery, Orthopaedic and Rheumatologic Institute, Cleveland Clinic Foundation, Cleveland, USA
| | - Muneaki Ishijima
- Department of Medicine for Orthopaedics and Motor Organ, Juntendo University Graduate School of Medicine, Tokyo, Japan
- Department of Orthopaedics, Faculty of Medicine, Juntendo University, Tokyo, Japan
- Department of Community Medicine and Research for Bone and Joint Diseases, Juntendo University Graduate School of Medicine, Tokyo, Japan
- Department of Pathophysiology for Locomotive Diseases, Juntendo University Graduate School of Medicine, Tokyo, Japan
| |
Collapse
|
2
|
Khalilzad Z, Tadj C. Use of psychoacoustic spectrum warping, decision template fusion, and neighborhood component analysis in newborn cry diagnostic systems. THE JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA 2024; 155:901-914. [PMID: 38310608 DOI: 10.1121/10.0024618] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Accepted: 01/10/2024] [Indexed: 02/06/2024]
Abstract
Dealing with newborns' health is a delicate matter since they cannot express needs, and crying does not reflect their condition. Although newborn cries have been studied for various purposes, there is no prior research on distinguishing a certain pathology from other pathologies so far. Here, an unsophisticated framework is proposed for the study of septic newborns amid a collective of other pathologies. The cry was analyzed with music inspired and speech processing inspired features. Furthermore, neighborhood component analysis (NCA) feature selection was employed with two goals: (i) Exploring how the elements of each feature set contributed to classification outcome; (ii) investigating to what extent the feature space could be compacted. The attained results showed success of both experiments introduced in this study, with 88.66% for the decision template fusion (DTF) technique and a consistent enhancement in comparison to all feature sets in terms of accuracy and 86.22% for the NCA feature selection method by drastically downsizing the feature space from 86 elements to only 6 elements. The achieved results showed great potential for identifying a certain pathology from other pathologies that may have similar effects on the cry patterns as well as proving the success of the proposed framework.
Collapse
Affiliation(s)
- Zahra Khalilzad
- Department of Electrical Engineering, École de Technologie Supérieur, Université du Québec, Montréal, Québec H3C 1K3, Canada
| | - Chakib Tadj
- Department of Electrical Engineering, École de Technologie Supérieur, Université du Québec, Montréal, Québec H3C 1K3, Canada
| |
Collapse
|
3
|
Reis ZSN, Pappa GL, Nader PDJH, do Vale MS, Silveira Neves G, Vitral GLN, Mussagy N, Norberto Dias IM, Romanelli RMDC. Respiratory distress syndrome prediction at birth by optical skin maturity assessment and machine learning models for limited-resource settings: a development and validation study. Front Pediatr 2023; 11:1264527. [PMID: 38054190 PMCID: PMC10694507 DOI: 10.3389/fped.2023.1264527] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/20/2023] [Accepted: 10/23/2023] [Indexed: 12/07/2023] Open
Abstract
Background A handheld optical device was developed to evaluate a newborn's skin maturity by assessing the photobiological properties of the tissue and processing it with other variables to predict early neonatal prognosis related to prematurity. This study assessed the device's ability to predict respiratory distress syndrome (RDS). Methods To assess the device's utility we enrolled newborns at childbirth in six urban perinatal centers from two multicenter single-blinded clinical trials. All newborns had inpatient follow-up until 72 h of life. We trained supervised machine learning models with data from 780 newborns in a Brazilian trial and provided external validation with data from 305 low-birth-weight newborns from another trial that assessed Brazilian and Mozambican newborns. The index test measured skin optical reflection with an optical sensor and adjusted acquired values with clinical variables such as birth weight and prenatal corticoid exposition for lung maturity, maternal diabetes, and hypertensive disturbances. The performance of the models was evaluated using intrasample k-parts cross-validation and external validation in an independent sample. Results Models adjusting three predictors (skin reflection, birth weight, and antenatal corticoid exposure) or five predictors had a similar performance, including or not maternal diabetes and hypertensive diseases. The best global accuracy was 89.7 (95% CI: 87.4 to 91.8, with a high sensitivity of 85.6% (80.2 to 90.0) and specificity of 91.3% (95% CI: 88.7 to 93.5). The test correctly discriminated RDS newborns in external validation, with 82.3% (95% CI: 77.5 to 86.4) accuracy. Our findings demonstrate a new way to assess a newborn's lung maturity, providing potential opportunities for earlier and more effective care. Trial registration RBR-3f5bm5 (online access: http://www.ensaiosclinicos.gov.br/rg/RBR-3f5bm5/), and RBR-33mjf (online access: https://ensaiosclinicos.gov.br/rg/RBR-33rnjf/).
Collapse
Affiliation(s)
| | - Gisele Lobo Pappa
- Departamento de Ciência da Computação, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
| | | | | | | | | | | | | | | |
Collapse
|
4
|
Zayed Y, Hasasneh A, Tadj C. Infant Cry Signal Diagnostic System Using Deep Learning and Fused Features. Diagnostics (Basel) 2023; 13:2107. [PMID: 37371002 DOI: 10.3390/diagnostics13122107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2023] [Revised: 06/09/2023] [Accepted: 06/13/2023] [Indexed: 06/29/2023] Open
Abstract
Early diagnosis of medical conditions in infants is crucial for ensuring timely and effective treatment. However, infants are unable to verbalize their symptoms, making it difficult for healthcare professionals to accurately diagnose their conditions. Crying is often the only way for infants to communicate their needs and discomfort. In this paper, we propose a medical diagnostic system for interpreting infants' cry audio signals (CAS) using a combination of different audio domain features and deep learning (DL) algorithms. The proposed system utilizes a dataset of labeled audio signals from infants with specific pathologies. The dataset includes two infant pathologies with high mortality rates, neonatal respiratory distress syndrome (RDS), sepsis, and crying. The system employed the harmonic ratio (HR) as a prosodic feature, the Gammatone frequency cepstral coefficients (GFCCs) as a cepstral feature, and image-based features through the spectrogram which are extracted using a convolution neural network (CNN) pretrained model and fused with the other features to benefit multiple domains in improving the classification rate and the accuracy of the model. The different combination of the fused features is then fed into multiple machine learning algorithms including random forest (RF), support vector machine (SVM), and deep neural network (DNN) models. The evaluation of the system using the accuracy, precision, recall, F1-score, confusion matrix, and receiver operating characteristic (ROC) curve, showed promising results for the early diagnosis of medical conditions in infants based on the crying signals only, where the system achieved the highest accuracy of 97.50% using the combination of the spectrogram, HR, and GFCC through the deep learning process. The finding demonstrated the importance of fusing different audio features, especially the spectrogram, through the learning process rather than a simple concatenation and the use of deep learning algorithms in extracting sparsely represented features that can be used later on in the classification problem, which improves the separation between different infants' pathologies. The results outperformed the published benchmark paper by improving the classification problem to be multiclassification (RDS, sepsis, and healthy), investigating a new type of feature, which is the spectrogram, using a new feature fusion technique, which is fusion, through the learning process using the deep learning model.
Collapse
Affiliation(s)
- Yara Zayed
- Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine
| | - Ahmad Hasasneh
- Department of Natural, Engineering and Technology Sciences, Faculty of Graduate Studies, Arab American University, Ramallah P.O. Box 240, Palestine
| | - Chakib Tadj
- Department of Electrical Engineering, École de Technologie Supérieur, Université du Québec, Montréal, QC H3C 1K3, Canada
| |
Collapse
|
5
|
Khalilzad Z, Tadj C. Using CCA-Fused Cepstral Features in a Deep Learning-Based Cry Diagnostic System for Detecting an Ensemble of Pathologies in Newborns. Diagnostics (Basel) 2023; 13:diagnostics13050879. [PMID: 36900023 PMCID: PMC10000938 DOI: 10.3390/diagnostics13050879] [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: 12/27/2022] [Revised: 02/14/2023] [Accepted: 02/21/2023] [Indexed: 03/02/2023] Open
Abstract
Crying is one of the means of communication for a newborn. Newborn cry signals convey precious information about the newborn's health condition and their emotions. In this study, cry signals of healthy and pathologic newborns were analyzed for the purpose of developing an automatic, non-invasive, and comprehensive Newborn Cry Diagnostic System (NCDS) that identifies pathologic newborns from healthy infants. For this purpose, Mel-frequency Cepstral Coefficients (MFCC) and Gammatone Frequency Cepstral Coefficients (GFCC) were extracted as features. These feature sets were also combined and fused through Canonical Correlation Analysis (CCA), which provides a novel manipulation of the features that have not yet been explored in the literature on NCDS designs, to the best of our knowledge. All the mentioned feature sets were fed to the Support Vector Machine (SVM) and Long Short-term Memory (LSTM). Furthermore, two Hyperparameter optimization methods, Bayesian and grid search, were examined to enhance the system's performance. The performance of our proposed NCDS was evaluated with two different datasets of inspiratory and expiratory cries. The CCA fusion feature set using the LSTM classifier accomplished the best F-score in the study, with 99.86% for the inspiratory cry dataset. The best F-score regarding the expiratory cry dataset, 99.44%, belonged to the GFCC feature set employing the LSTM classifier. These experiments suggest the high potential and value of using the newborn cry signals in the detection of pathologies. The framework proposed in this study can be implemented as an early diagnostic tool for clinical studies and help in the identification of pathologic newborns.
Collapse
|