1
|
Cuna A, Premkumar MH, Sampath V. Artificial intelligence to classify acquired intestinal injury in preterm neonates-a new perspective. Pediatr Res 2024; 96:30-32. [PMID: 38499626 DOI: 10.1038/s41390-024-03148-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/28/2024] [Accepted: 03/02/2024] [Indexed: 03/20/2024]
Affiliation(s)
- Alain Cuna
- Division of Neonatology, Children's Mercy Kansas City, Kansas City, MO, USA
- School of Medicine, University of Missouri Kansas City, Kansas City, MO, USA
| | - Muralidhar H Premkumar
- Division of Neonatology, Baylor College of Medicine, Texas Children's Hospital, Houston, TX, USA
| | - Venkatesh Sampath
- Division of Neonatology, Children's Mercy Kansas City, Kansas City, MO, USA.
- School of Medicine, University of Missouri Kansas City, Kansas City, MO, USA.
| |
Collapse
|
2
|
Bethell GS, Jones IH, Battersby C, Knight M, Hall NJ. Methods of identifying surgical Necrotizing Enterocolitis-a systematic review and meta-analysis. Pediatr Res 2024:10.1038/s41390-024-03292-3. [PMID: 38849483 DOI: 10.1038/s41390-024-03292-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Revised: 04/02/2024] [Accepted: 05/15/2024] [Indexed: 06/09/2024]
Abstract
BACKGROUND Current data suggests potential benefit of earlier surgery for necrotizing enterocolitis (NEC) however this requires accurate prognostication early in the disease course. This study aims to identify and determine the effectiveness of previously reported methods or tests for the identification of surgical NEC. METHODS Systematic review and meta-analysis with registration on PROSPERO including articles describing a method of identifying surgical NEC. Outcomes of interest were effectiveness and repeatability of index test. RESULTS Of the 190 full-text articles screened, 90 studies were included which contained 114 methods of identifying surgical NEC in 9546 infants. Of these methods, 44 were a scoring system, 37 a single biomarker, 24 an imaging method, and 9 an invasive method. Sensitivity and specificity ranged from 12.8-100% to 13-100%, respectively. Some methods (9.6%) provided insufficient methods for repeatability within clinical practice or research. Meta-analyses were possible for only 2 methods, the metabolic derangement 7 score and abdominal ultrasound. CONCLUSIONS A range of methods for identifying surgical NEC have been identified with varying overall performance and uncertainties about reproducibility and superiority of any method. External validation in large multicentre datasets should allow direct comparison of accuracy and prospective study should evaluate impact on clinical outcomes. IMPACT Earlier identification of need for surgery in necrotizing enterocolitis (NEC) has the potential to improve the unfavourable outcomes in this condition. As such, many methods have been developed and reported to allow earlier identification of surgical NEC. This study is the first synthesis of the literature which identifies previously reported methods and the effectiveness of these. Many methods, including scoring systems and biomarkers, appear effective for prognostication in NEC and external validation is now required in multicentre datasets prior to clinical utility.
Collapse
Affiliation(s)
- George S Bethell
- University Surgical Unit, Faculty of Medicine, University of Southampton, Southampton, UK
- Department of Paediatric Surgery and Urology, Southampton Children's Hospital, Southampton, UK
| | - Ian H Jones
- Department of Paediatric Surgery and Urology, Birmingham Children's Hospital, Birmingham, UK
| | - Cheryl Battersby
- Neonatal Medicine, School of Public Health, Faculty of Medicine, Imperial College London, London, UK
| | - Marian Knight
- Nuffield Department of Population Health, National Perinatal Epidemiology Unit, University of Oxford, Oxford, UK
| | - Nigel J Hall
- University Surgical Unit, Faculty of Medicine, University of Southampton, Southampton, UK.
- Department of Paediatric Surgery and Urology, Southampton Children's Hospital, Southampton, UK.
| |
Collapse
|
3
|
Kim SH, Oh YJ, Son J, Jung D, Kim D, Ryu SR, Na JY, Hwang JK, Kim TH, Park HK. Machine learning-based analysis for prediction of surgical necrotizing enterocolitis in very low birth weight infants using perinatal factors: a nationwide cohort study. Eur J Pediatr 2024; 183:2743-2751. [PMID: 38554173 PMCID: PMC11098869 DOI: 10.1007/s00431-024-05505-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/30/2023] [Revised: 02/20/2024] [Accepted: 03/02/2024] [Indexed: 04/01/2024]
Abstract
Early prediction of surgical necrotizing enterocolitis (sNEC) in preterm infants is important. However, owing to the complexity of the disease, identifying infants with NEC at a high risk for surgical intervention is difficult. We developed a machine learning (ML) algorithm to predict sNEC using perinatal factors obtained from the national cohort registry of very low birth weight (VLBW) infants. Data were collected from the medical records of 16,385 VLBW infants registered in the Korean Neonatal Network (KNN). Infants who underwent surgical intervention were identified with sNEC, and infants who received medical treatment, with medical NEC (mNEC). We used 38 variables, including maternal, prenatal, and postnatal factors that were obtained within 1 week of birth, for training. A total of 1085 patients had NEC (654 with sNEC and 431 with mNEC). VLBW infants showed a higher incidence of sNEC at a lower gestational age (GA) (p < 0.001). Our proposed ensemble model showed an area under the receiver operating characteristic curve of 0.721 for sNEC prediction. Conclusion: Proposed ensemble model may help predict which infants with NEC are likely to develop sNEC. Through early prediction and prompt intervention, prognosis of sNEC may be improved. What is Known: • Machine learning (ML)-based techniques have been employed in NEC research for prediction, diagnosis, and prognosis, with promising outcomes. • While most studies have utilized abdominal radiographs and clinical manifestations of NEC as data sources, and have demonstrated their usefulness, they may prove weak in terms of early prediction. What is New: • We analyzed the perinatal factors of VLBW infants acquired within 7 days of birth and used ML-based analysis to identify which infants with NEC are vulnerable to clinical deterioration and at high risk for surgical intervention using nationwide cohort data.
Collapse
Affiliation(s)
- Seung Hyun Kim
- Department of Pediatrics, Hanyang University College of Medicine, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
- Department of Pediatrics, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81, Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea
| | - Yoon Ju Oh
- Department of Artificial Intelligence, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Joonhyuk Son
- Department of Pediatric Surgery, Hanyang University College of Medicine, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Donggoo Jung
- Department of Artificial Intelligence, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Daehyun Kim
- Department of Artificial Intelligence, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Soo Rack Ryu
- Biostatistical Consulting and Research Lab, Medical Research Collaborating Center, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Jae Yoon Na
- Department of Pediatrics, Hanyang University College of Medicine, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Jae Kyoon Hwang
- Department of Pediatrics, Hanyang University College of Medicine, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea
| | - Tae Hyun Kim
- Department of Computer Science, Hanyang University, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea.
| | - Hyun-Kyung Park
- Department of Pediatrics, Hanyang University College of Medicine, 222 Wangsimni-ro, Seongdong-gu, Seoul, 04763, Republic of Korea.
| |
Collapse
|
4
|
Roy-García IA, Paredes-Manjarrez C, Moreno-Palacios J, Rivas-Ruiz R, Flores-Pulido AA. [ROC curves: general characteristics and their usefulness in clinical practice]. REVISTA MEDICA DEL INSTITUTO MEXICANO DEL SEGURO SOCIAL 2023; 61:S497-S502. [PMID: 37935015 PMCID: PMC10754459 DOI: 10.5281/zenodo.8319791] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 01/13/2023] [Accepted: 02/15/2023] [Indexed: 11/09/2023]
Abstract
The use of diagnostic tests to determine the presence or absence of a disease is essential in clinical practice. The results of a diagnostic test may correspond to numerical estimates that require quantitative reference parameters to be transferred to a dichotomous interpretation as normal or abnormal and thus implement actions for the care of a condition or disease. For example, in the diagnosis of anemia it is necessary to define a cut-off point for the hemoglobin variable and create two categories that distinguish the presence or absence of anemia. The method used for this process is the preparation of diagnostic performance curves, better known by their acronym in English as ROC (Receiver Operating Characteristic). The ROC curve is also useful as a prognostic marker, since it allows defining the cut-off point of a quantitative variable that is associated with greater mortality or risk of complications. They have been used in different prognostic markers in COVID-19, such as the neutrophil/lymphocyte ratio and D-dimer, in which cut-off points associated with mortality and/or risk of mechanical ventilation were identified. The ROC curve is used to evaluate the diagnostic performance of a test in isolation, but it can also be used to compare the performance of two or more diagnostic tests and define which one is more accurate. This article describes the basic concepts for the use and interpretation of the ROC curve, the interpretation of an area under the curve (AUC) and the comparison of two or more diagnostic tests.
Collapse
Affiliation(s)
- Ivonne Analí Roy-García
- Instituto Mexicano del Seguro Social, Coordinación de Investigación en Salud, Centro de Adiestramiento e Investigación Clínica. Ciudad de México, MéxicoInstituto Mexicano del Seguro SocialMéxico
- Instituto Politécnico Nacional, Escuela Superior de Medicina, Sección de Posgrado. Ciudad de México, MéxicoInstituto Politécnico NacionalMéxico
| | - Carlos Paredes-Manjarrez
- Instituto Mexicano del Seguro Social, Centro Médico Nacional Siglo XXI, Hospital de Especialidades, Departamento de Imagenología. Ciudad de México, MéxicoInstituto Mexicano del Seguro SocialMéxico
| | - Jorge Moreno-Palacios
- Instituto Mexicano del Seguro Social, Centro Médico Nacional Siglo XXI, Hospital de Especialidades, Departamento de Urología. Ciudad de México, MéxicoInstituto Mexicano del Seguro SocialMéxico
| | - Rodolfo Rivas-Ruiz
- Instituto Mexicano del Seguro Social, Coordinación de Investigación en Salud, Centro de Adiestramiento e Investigación Clínica. Ciudad de México, MéxicoInstituto Mexicano del Seguro SocialMéxico
| | - Andrey Arturo Flores-Pulido
- Instituto Politécnico Nacional, Escuela Superior de Medicina, Sección de Posgrado. Ciudad de México, MéxicoInstituto Politécnico NacionalMéxico
- Secretaría de Salud, Centro Regional de Alta Especialidad, Hospital de Especialidades Pediátricas. Tuxtla Gutiérrez, Chiapas, MéxicoSecretaría de SaludMéxico
| |
Collapse
|
5
|
McElroy SJ, Lueschow SR. State of the art review on machine learning and artificial intelligence in the study of neonatal necrotizing enterocolitis. Front Pediatr 2023; 11:1182597. [PMID: 37303753 PMCID: PMC10250644 DOI: 10.3389/fped.2023.1182597] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 04/25/2023] [Indexed: 06/13/2023] Open
Abstract
Necrotizing Enterocolitis (NEC) is one of the leading causes of gastrointestinal emergency in preterm infants. Although NEC was formally described in the 1960's, there is still difficulty in diagnosis and ultimately treatment for NEC due in part to the multifactorial nature of the disease. Artificial intelligence (AI) and machine learning (ML) techniques have been applied by healthcare researchers over the past 30 years to better understand various diseases. Specifically, NEC researchers have used AI and ML to predict NEC diagnosis, NEC prognosis, discover biomarkers, and evaluate treatment strategies. In this review, we discuss AI and ML techniques, the current literature that has applied AI and ML to NEC, and some of the limitations in the field.
Collapse
Affiliation(s)
- Steven J. McElroy
- Department of Pediatrics, University of California Davis, Sacramento, CA, United States
| | - Shiloh R. Lueschow
- Stead Family Department of Pediatrics, University of Iowa, Iowa City, IA, United States
| |
Collapse
|
6
|
Hamraz M, Ali A, Mashwani WK, Aldahmani S, Khan Z. Feature selection for high dimensional microarray gene expression data via weighted signal to noise ratio. PLoS One 2023; 18:e0284619. [PMID: 37098036 PMCID: PMC10128961 DOI: 10.1371/journal.pone.0284619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Accepted: 04/04/2023] [Indexed: 04/26/2023] Open
Abstract
Feature selection in high dimensional gene expression datasets not only reduces the dimension of the data, but also the execution time and computational cost of the underlying classifier. The current study introduces a novel feature selection method called weighted signal to noise ratio (WSNR) by exploiting the weights of features based on support vectors and signal to noise ratio, with an objective to identify the most informative genes in high dimensional classification problems. The combination of two state-of-the-art procedures enables the extration of the most informative genes. The corresponding weights of these procedures are then multiplied and arranged in decreasing order. Larger weight of a feature indicates its discriminatory power in classifying the tissue samples to their true classes. The current method is validated on eight gene expression datasets. Moreover, results of the proposed method (WSNR) are also compared with four well known feature selection methods. We found that the (WSNR) outperform the other competing methods on 6 out of 8 datasets. Box-plots and Bar-plots of the results of the proposed method and all the other methods are also constructed. The proposed method is further assessed on simulated data. Simulation analysis reveal that (WSNR) outperforms all the other methods included in the study.
Collapse
Affiliation(s)
- Muhammad Hamraz
- Department of Statistics, Abdul Wali Khan University Mardan, Mardan, Pakistan
| | - Amjad Ali
- Department of Statistics, Abdul Wali Khan University Mardan, Mardan, Pakistan
| | - Wali Khan Mashwani
- Institute of Numerical Sciences, Kohat University of Science and Technology, Kohat, Pakistan
| | - Saeed Aldahmani
- Department of Analytics in the Digital Era, United Arab Emirates University, Al Ain, UAE
| | - Zardad Khan
- Department of Analytics in the Digital Era, United Arab Emirates University, Al Ain, UAE
| |
Collapse
|