1
|
Seo HW, Oh YJ, Oh J, Lee DK, Lee SH, Chung JH, Kim TH. Prediction of hearing recovery with deep learning algorithm in sudden sensorineural hearing loss. Sci Rep 2024; 14:20058. [PMID: 39209945 PMCID: PMC11362143 DOI: 10.1038/s41598-024-70436-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2024] [Accepted: 08/16/2024] [Indexed: 09/04/2024] Open
Abstract
This study aimed to establish a deep learning-based predictive model for the prognosis of idiopathic sudden sensorineural hearing loss (SSNHL). Data from 1108 patients with SSNHL between January 2015 and May 2023 were retrospectively analyzed. Patients underwent standardized treatment protocols including high-dose steroid therapy and hearing outcomes were assessed after three months using Siegel's criteria and the American Academy of Otolaryngology-Head and Neck Surgery (AAO-HNS) classification. For predicting patient recovery, a two-layered classification process was implemented. Initially, a set of 22 Multilayer Perceptrons (MLP) networks was employed to categorize the patients. The outcomes from this initial categorization were subsequently relayed to a second-layer meta-classifier for final prognosis determination. The validity of this methodology was ascertained through a K-fold cross-validation procedure executed with 10 distinct splits. The prediction model for complete recovery, based on Siegel's criteria, demonstrated an accuracy of 0.892 and area under the curve (AUC) of 0.922. For the class A prediction, according to AAO-HNS classification, the model showed an accuracy of 0.847 and AUC of 0.918. These results suggest that the model may have the potential to contribute to the establishment of tailored patient management strategies by predicting hearing recovery in patients with SSNHL.
Collapse
Affiliation(s)
- Hee Won Seo
- Department of Otolaryngology-Head and Neck Surgery, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Young Jae Oh
- Department of Computer Science, Hanyang University, Seoul, Republic of Korea
| | - Jaehoon Oh
- Department of Emergency Medicine, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Dong Keon Lee
- Department of Emergency Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Seung Hwan Lee
- Department of Otolaryngology-Head and Neck Surgery, College of Medicine, Hanyang University, Seoul, Republic of Korea
| | - Jae Ho Chung
- Department of Otolaryngology-Head and Neck Surgery, College of Medicine, Hanyang University, Seoul, Republic of Korea.
| | - Tae Hyun Kim
- Department of Computer Science, Hanyang University, Seoul, Republic of Korea.
| |
Collapse
|
2
|
Fabijan A, Zawadzka-Fabijan A, Fabijan R, Zakrzewski K, Nowosławska E, Polis B. Assessing the Accuracy of Artificial Intelligence Models in Scoliosis Classification and Suggested Therapeutic Approaches. J Clin Med 2024; 13:4013. [PMID: 39064053 PMCID: PMC11278075 DOI: 10.3390/jcm13144013] [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: 06/07/2024] [Revised: 06/30/2024] [Accepted: 07/06/2024] [Indexed: 07/28/2024] Open
Abstract
Background: Open-source artificial intelligence models (OSAIMs) are increasingly being applied in various fields, including IT and medicine, offering promising solutions for diagnostic and therapeutic interventions. In response to the growing interest in AI for clinical diagnostics, we evaluated several OSAIMs-such as ChatGPT 4, Microsoft Copilot, Gemini, PopAi, You Chat, Claude, and the specialized PMC-LLaMA 13B-assessing their abilities to classify scoliosis severity and recommend treatments based on radiological descriptions from AP radiographs. Methods: Our study employed a two-stage methodology, where descriptions of single-curve scoliosis were analyzed by AI models following their evaluation by two independent neurosurgeons. Statistical analysis involved the Shapiro-Wilk test for normality, with non-normal distributions described using medians and interquartile ranges. Inter-rater reliability was assessed using Fleiss' kappa, and performance metrics, like accuracy, sensitivity, specificity, and F1 scores, were used to evaluate the AI systems' classification accuracy. Results: The analysis indicated that although some AI systems, like ChatGPT 4, Copilot, and PopAi, accurately reflected the recommended Cobb angle ranges for disease severity and treatment, others, such as Gemini and Claude, required further calibration. Particularly, PMC-LLaMA 13B expanded the classification range for moderate scoliosis, potentially influencing clinical decisions and delaying interventions. Conclusions: These findings highlight the need for the continuous refinement of AI models to enhance their clinical applicability.
Collapse
Affiliation(s)
- Artur Fabijan
- Department of Neurosurgery, Polish-Mother’s Memorial Hospital Research Institute, 93-338 Lodz, Poland; (K.Z.); (E.N.); (B.P.)
| | - Agnieszka Zawadzka-Fabijan
- Department of Rehabilitation Medicine, Faculty of Health Sciences, Medical University of Lodz, 90-419 Lodz, Poland;
| | | | - Krzysztof Zakrzewski
- Department of Neurosurgery, Polish-Mother’s Memorial Hospital Research Institute, 93-338 Lodz, Poland; (K.Z.); (E.N.); (B.P.)
| | - Emilia Nowosławska
- Department of Neurosurgery, Polish-Mother’s Memorial Hospital Research Institute, 93-338 Lodz, Poland; (K.Z.); (E.N.); (B.P.)
| | - Bartosz Polis
- Department of Neurosurgery, Polish-Mother’s Memorial Hospital Research Institute, 93-338 Lodz, Poland; (K.Z.); (E.N.); (B.P.)
| |
Collapse
|
3
|
Islam MN, Islam MS, Shourav NH, Rahman I, Faisal FA, Islam MM, Sarker IH. Exploring post-COVID-19 health effects and features with advanced machine learning techniques. Sci Rep 2024; 14:9884. [PMID: 38688931 DOI: 10.1038/s41598-024-60504-w] [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: 12/03/2023] [Accepted: 04/23/2024] [Indexed: 05/02/2024] Open
Abstract
COVID-19 is an infectious respiratory disease that has had a significant impact, resulting in a range of outcomes including recovery, continued health issues, and the loss of life. Among those who have recovered, many experience negative health effects, particularly influenced by demographic factors such as gender and age, as well as physiological and neurological factors like sleep patterns, emotional states, anxiety, and memory. This research aims to explore various health factors affecting different demographic profiles and establish significant correlations among physiological and neurological factors in the post-COVID-19 state. To achieve these objectives, we have identified the post-COVID-19 health factors and based on these factors survey data were collected from COVID-recovered patients in Bangladesh. Employing diverse machine learning algorithms, we utilised the best prediction model for post-COVID-19 factors. Initial findings from statistical analysis were further validated using Chi-square to demonstrate significant relationships among these elements. Additionally, Pearson's coefficient was utilized to indicate positive or negative associations among various physiological and neurological factors in the post-COVID-19 state. Finally, we determined the most effective machine learning model and identified key features using analytical methods such as the Gini Index, Feature Coefficients, Information Gain, and SHAP Value Assessment. And found that the Decision Tree model excelled in identifying crucial features while predicting the extent of post-COVID-19 impact.
Collapse
Affiliation(s)
- Muhammad Nazrul Islam
- Department of Computer Science and Engineering, Military Institute of Science and Technology, Mirpur Cantonment, Dhaka, 1216, Bangladesh.
| | - Md Shofiqul Islam
- Department of Computer Science and Engineering, Military Institute of Science and Technology, Mirpur Cantonment, Dhaka, 1216, Bangladesh
| | - Nahid Hasan Shourav
- Department of Computer Science and Engineering, Military Institute of Science and Technology, Mirpur Cantonment, Dhaka, 1216, Bangladesh
| | - Iftiaqur Rahman
- Department of Computer Science and Engineering, Military Institute of Science and Technology, Mirpur Cantonment, Dhaka, 1216, Bangladesh
| | - Faiz Al Faisal
- Department of Computer Science and Engineering, Green University of Bangladesh, Dhaka, Bangladesh
| | - Md Motaharul Islam
- Department of Computer Science and Engineering, United International University, Dhaka, 1212, Bangladesh
| | - Iqbal H Sarker
- School of Science, Edith Cowan University, Perth, WA, 6027, Australia
| |
Collapse
|
4
|
Yakovyna V, Shakhovska N, Szpakowska A. A novel hybrid supervised and unsupervised hierarchical ensemble for COVID-19 cases and mortality prediction. Sci Rep 2024; 14:9782. [PMID: 38684770 PMCID: PMC11059164 DOI: 10.1038/s41598-024-60637-y] [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: 12/15/2023] [Accepted: 04/25/2024] [Indexed: 05/02/2024] Open
Abstract
Though COVID-19 is no longer a pandemic but rather an endemic, the epidemiological situation related to the SARS-CoV-2 virus is developing at an alarming rate, impacting every corner of the world. The rapid escalation of the coronavirus has led to the scientific community engagement, continually seeking solutions to ensure the comfort and safety of society. Understanding the joint impact of medical and non-medical interventions on COVID-19 spread is essential for making public health decisions that control the pandemic. This paper introduces two novel hybrid machine-learning ensembles that combine supervised and unsupervised learning for COVID-19 data classification and regression. The study utilizes publicly available COVID-19 outbreak and potential predictive features in the USA dataset, which provides information related to the outbreak of COVID-19 disease in the US, including data from each of 3142 US counties from the beginning of the epidemic (January 2020) until June 2021. The developed hybrid hierarchical classifiers outperform single classification algorithms. The best-achieved performance metrics for the classification task were Accuracy = 0.912, ROC-AUC = 0.916, and F1-score = 0.916. The proposed hybrid hierarchical ensemble combining both supervised and unsupervised learning allows us to increase the accuracy of the regression task by 11% in terms of MSE, 29% in terms of the area under the ROC, and 43% in terms of the MPP metric. Thus, using the proposed approach, it is possible to predict the number of COVID-19 cases and deaths based on demographic, geographic, climatic, traffic, public health, social-distancing-policy adherence, and political characteristics with sufficiently high accuracy. The study reveals that virus pressure is the most important feature in COVID-19 spread for classification and regression analysis. Five other significant features were identified to have the most influence on COVID-19 spread. The combined ensembling approach introduced in this study can help policymakers design prevention and control measures to avoid or minimize public health threats in the future.
Collapse
Affiliation(s)
- Vitaliy Yakovyna
- Faculty of Mathematics and Computer Science, University of Warmia and Mazury in Olsztyn, Ul. Oczapowskiego 2, 10-719, Olsztyn, Poland
- Artificial Intelligence Department, Lviv Polytechnic National University, 12 S. Bandery St, Lviv, 79013, Ukraine
| | - Nataliya Shakhovska
- Artificial Intelligence Department, Lviv Polytechnic National University, 12 S. Bandery St, Lviv, 79013, Ukraine.
- Universytet Rolniczy, 31120, Kraków, Poland.
| | - Aleksandra Szpakowska
- Faculty of Mathematics and Computer Science, University of Warmia and Mazury in Olsztyn, Ul. Oczapowskiego 2, 10-719, Olsztyn, Poland
| |
Collapse
|
5
|
Ponthier L, Autmizguine J, Franck B, Åsberg A, Ovetchkine P, Destere A, Marquet P, Labriffe M, Woillard JB. Optimization of Ganciclovir and Valganciclovir Starting Dose in Children by Machine Learning. Clin Pharmacokinet 2024:10.1007/s40262-024-01362-7. [PMID: 38492206 DOI: 10.1007/s40262-024-01362-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 02/15/2024] [Indexed: 03/18/2024]
Abstract
BACKGROUND AND OBJECTIVES Ganciclovir (GCV) and valganciclovir (VGCV) show large interindividual pharmacokinetic variability, particularly in children. The objectives of this study were (1) to develop machine learning (ML) algorithms trained on simulated pharmacokinetics profiles obtained by Monte Carlo simulations to estimate the best ganciclovir or valganciclovir starting dose in children and (2) to compare its performances on real-world profiles to previously published equation derived from literature population pharmacokinetic (POPPK) models achieving about 20% of profiles within the target. MATERIALS AND METHODS The pharmacokinetic parameters of four literature POPPK models in addition to the World Health Organization (WHO) growth curve for children were used in the mrgsolve R package to simulate 10,800 pharmacokinetic profiles. ML algorithms were developed and benchmarked to predict the probability to reach the steady-state, area-under-the-curve target (AUC0-24 within 40-60 mg × h/L) based on demographic characteristics only. The best ML algorithm was then used to calculate the starting dose maximizing the target attainment. Performances were evaluated for ML and literature formula in a test set and in an external set of 32 and 31 actual patients (GCV and VGCV, respectively). RESULTS A combination of Xgboost, neural network, and random forest algorithms yielded the best performances and highest target attainment in the test set (36.8% for GCV and 35.3% for the VGCV). In actual patients, the best GCV ML starting dose yielded the highest target attainment rate (25.8%) and performed equally for VGCV with the Franck model formula (35.3% for both). CONCLUSION The ML algorithms exhibit good performances in comparison with previously validated models and should be evaluated prospectively.
Collapse
Affiliation(s)
- Laure Ponthier
- Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, 87000, Limoges, France
- Department of Pediatrics, University Hospital of Limoges, Limoges, France
| | - Julie Autmizguine
- Research Center, Centre Hospitalier Universitaire Sainte-Justine, Montreal, QC, Canada
- Department of Pediatrics, Centre Hospitalier Universitaire Sainte-Justine, Montreal, QC, Canada
- Department of Pharmacology and Physiology, Université de Montréal, Montreal, QC, Canada
| | - Benedicte Franck
- Department of Clinical and Biological Pharmacology and Pharmacovigilance, Clinical Investigation Center, CIC-P 1414, Rennes, France
- University of Rennes, Centre Hospitalier Universitaire Rennes, École des Hautes Études en Santé Publique, IRSET (Institut de Recherche en Santé, Environnement et Travail), UMR S 1085, Rennes, France
| | - Anders Åsberg
- Department of Transplantation Medicine, Oslo University Hospital-Rikshospitalet, Oslo, Norway
- Section of Pharmacology and Pharmaceutical Biosciences, Department of Pharmacy, University of Oslo, Oslo, Norway
| | - Philippe Ovetchkine
- Department of Pediatrics, Centre Hospitalier Universitaire Sainte-Justine, Montreal, QC, Canada
| | - Alexandre Destere
- Department of Pharmacology, Toxicology and Pharmacovigilance, University Hospital of Nice, Nice, France
| | - Pierre Marquet
- Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, 87000, Limoges, France
- Department of Pharmacology, Toxicology and Pharmacovigilance, University Hospital of Limoges, Limoges, France
| | - Marc Labriffe
- Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, 87000, Limoges, France
- Department of Pharmacology, Toxicology and Pharmacovigilance, University Hospital of Limoges, Limoges, France
| | - Jean-Baptiste Woillard
- Pharmacology and Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, 87000, Limoges, France.
- Department of Pharmacology, Toxicology and Pharmacovigilance, University Hospital of Limoges, Limoges, France.
| |
Collapse
|
6
|
Pisano F, Cannas B, Fanni A, Pasella M, Canetto B, Giglio SR, Mocci S, Chessa L, Perra A, Littera R. Decision trees for early prediction of inadequate immune response to coronavirus infections: a pilot study on COVID-19. Front Med (Lausanne) 2023; 10:1230733. [PMID: 37601789 PMCID: PMC10433226 DOI: 10.3389/fmed.2023.1230733] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Accepted: 07/19/2023] [Indexed: 08/22/2023] Open
Abstract
Introduction Few artificial intelligence models exist to predict severe forms of COVID-19. Most rely on post-infection laboratory data, hindering early treatment for high-risk individuals. Methods This study developed a machine learning model to predict inherent risk of severe symptoms after contracting SARS-CoV-2. Using a Decision Tree trained on 153 Alpha variant patients, demographic, clinical and immunogenetic markers were considered. Model performance was assessed on Alpha and Delta variant datasets. Key risk factors included age, gender, absence of KIR2DS2 gene (alone or with HLA-C C1 group alleles), presence of 14-bp polymorphism in HLA-G gene, presence of KIR2DS5 gene, and presence of KIR telomeric region A/A. Results The model achieved 83.01% accuracy for Alpha variant and 78.57% for Delta variant, with True Positive Rates of 80.82 and 77.78%, and True Negative Rates of 85.00% and 79.17%, respectively. The model showed high sensitivity in identifying individuals at risk. Discussion The present study demonstrates the potential of AI algorithms, combined with demographic, epidemiologic, and immunogenetic data, in identifying individuals at high risk of severe COVID-19 and facilitating early treatment. Further studies are required for routine clinical integration.
Collapse
Affiliation(s)
- Fabio Pisano
- Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy
| | - Barbara Cannas
- Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy
| | - Alessandra Fanni
- Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy
| | - Manuela Pasella
- Department of Electrical and Electronic Engineering, University of Cagliari, Cagliari, Italy
| | | | - Sabrina Rita Giglio
- Medical Genetics, Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy
- AART-ODV (Association for the Advancement of Research on Transplantation), Cagliari, Italy
- Medical Genetics, R. Binaghi Hospital, Local Public Health and Social Care Unit (ASSL) of Cagliari, Cagliari, Italy
- Centre for Research University Services (CeSAR, Centro Servizi di Ateneo per la Ricerca), University of Cagliari, Cagliari, Monserrato, Italy
| | - Stefano Mocci
- Medical Genetics, Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy
- Centre for Research University Services (CeSAR, Centro Servizi di Ateneo per la Ricerca), University of Cagliari, Cagliari, Monserrato, Italy
| | - Luchino Chessa
- AART-ODV (Association for the Advancement of Research on Transplantation), Cagliari, Italy
- Department of Medical Sciences and Public Health, University of Cagliari, Cagliari, Italy
- Liver Unit, Department of Internal Medicine, University Hospital of Cagliari, Cagliari, Italy
| | - Andrea Perra
- AART-ODV (Association for the Advancement of Research on Transplantation), Cagliari, Italy
- Unit of Oncology and Molecular Pathology, Department of Biomedical Sciences, University of Cagliari, Cagliari, Italy
| | - Roberto Littera
- AART-ODV (Association for the Advancement of Research on Transplantation), Cagliari, Italy
- Medical Genetics, R. Binaghi Hospital, Local Public Health and Social Care Unit (ASSL) of Cagliari, Cagliari, Italy
| |
Collapse
|
7
|
Robust Classification and Detection of Big Medical Data Using Advanced Parallel K-Means Clustering, YOLOv4, and Logistic Regression. Life (Basel) 2023; 13:life13030691. [PMID: 36983845 PMCID: PMC10056696 DOI: 10.3390/life13030691] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Revised: 02/24/2023] [Accepted: 02/28/2023] [Indexed: 03/08/2023] Open
Abstract
Big-medical-data classification and image detection are crucial tasks in the field of healthcare, as they can assist with diagnosis, treatment planning, and disease monitoring. Logistic regression and YOLOv4 are popular algorithms that can be used for these tasks. However, these techniques have limitations and performance issue with big medical data. In this study, we presented a robust approach for big-medical-data classification and image detection using logistic regression and YOLOv4, respectively. To improve the performance of these algorithms, we proposed the use of advanced parallel k-means pre-processing, a clustering technique that identified patterns and structures in the data. Additionally, we leveraged the acceleration capabilities of a neural engine processor to further enhance the speed and efficiency of our approach. We evaluated our approach on several large medical datasets and showed that it could accurately classify large amounts of medical data and detect medical images. Our results demonstrated that the combination of advanced parallel k-means pre-processing, and the neural engine processor resulted in a significant improvement in the performance of logistic regression and YOLOv4, making them more reliable for use in medical applications. This new approach offers a promising solution for medical data classification and image detection and may have significant implications for the field of healthcare.
Collapse
|
8
|
Izonin I, Shakhovska N. Special issue: informatics & data-driven medicine-2021. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2022; 19:9769-9772. [PMID: 36031967 DOI: 10.3934/mbe.2022454] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Modern medical diagnosis, treatment, or rehabilitation problems of the patient reach completely different levels due to the rapid development of artificial intelligence tools. Methods of machine learning and optimization based on the intersection of historical data of various volumes provide significant support to physicians in the form of accurate and fast solutions of automated diagnostic systems. It significantly improves the quality of medical services. This special issue deals with the problems of medical diagnosis and prognosis in the case of short datasets. The problem is not new, but existing machine learning methods do not always demonstrate the adequacy of prediction or classification models, especially in the case of limited data to implement the training procedures. That is why the improvement of existing and development of new artificial intelligence tools that will be able to solve it effectively is an urgent task. The special issue contains the latest achievements in medical diagnostics based on the processing of small numerical and image-based datasets. Described methods have a strong theoretical basis, and numerous experimental studies confirm the high efficiency of their application in various applied fields of Medicine.
Collapse
Affiliation(s)
- Ivan Izonin
- Department of Artificial Intelligence, Lviv Polytechnic National University, Kniazia Romana str., 5, Lviv 79905, Ukraine
| | - Nataliya Shakhovska
- Department of Artificial Intelligence, Lviv Polytechnic National University, Kniazia Romana str., 5, Lviv 79905, Ukraine
| |
Collapse
|