1
|
Chen X, Xu D, Gu X, Li Z, Zhang Y, Wu P, Huang Z, Zhang J, Li Y. Machine learning in prenatal MRI predicts postnatal ventricular abnormalities in fetuses with isolated ventriculomegaly. Eur Radiol 2024:10.1007/s00330-024-10785-6. [PMID: 38730032 DOI: 10.1007/s00330-024-10785-6] [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: 02/13/2024] [Revised: 03/15/2024] [Accepted: 03/21/2024] [Indexed: 05/12/2024]
Abstract
OBJECTIVES To evaluate the intracranial structures and brain parenchyma radiomics surrounding the occipital horn of the lateral ventricle in normal fetuses (NFs) and fetuses with ventriculomegaly (FVs), as well as to predict postnatally enlarged lateral ventricle alterations in FVs. METHODS Between January 2014 and August 2023, 141 NFs and 101 FVs underwent 1.5 T balanced steady-state free precession (BSSFP), including 68 FVs with resolved lateral ventricles (FVM-resolved) and 33 FVs with stable lateral ventricles (FVM-stable). Demographic data and intracranial structures were analyzed. To predict the enlarged ventricle alterations of FVs postnatally, logistic regression models with 5-fold cross-validation were developed based on lateral ventricle morphology, blended-cortical or/and subcortical radiomics characteristics. Validation of the models' performance was conducted using the receiver operating characteristic curve (ROC), calibration curve, and decision curve analysis (DCA). RESULTS Significant alterations in cerebral structures were observed between NFs and FVs (p < 0.05), excluding the maximum frontal horn diameter (FD). However, there was no notable distinction between the FVM-resolved and FVM-stable groups (all p > 0.05). Based on subcortical-radiomics on the aberrant sides of FVs, this approach exhibited high efficacy in distinguishing NFs from FVs in the training/validation set, yielding an impressive AUC of 1/0.992. With an AUC value of 0.822/0.743 in the training/validation set, the Subcortical-radiomics model demonstrated its ability to predict lateral ventricle alterations in FVs, which had the greatest predictive advantages indicated by DCA. CONCLUSIONS Microstructural alterations in subcortical parenchyma associated with ventriculomegaly can serve as predictive indicators for postnatal lateral ventricle variations in FVs. CLINICAL RELEVANCE STATEMENT It is critical to gain pertinent information from a solitary fetal MRI to anticipate postnatal lateral ventricle alterations in fetuses with ventriculomegaly. This approach holds the potential to diminish the necessity for recurrent prenatal ultrasound or MRI examinations. KEY POINTS Fetal ventriculomegaly is a dynamic condition that affects postnatal neurodevelopment. Machine learning and subcortical-radiomics can predict postnatal alterations in the lateral ventricle. Machine learning, applied to single-fetal MRI, might reduce required antenatal testing.
Collapse
Affiliation(s)
- Xue Chen
- Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou City, Jiangsu Province, 215002, China
| | - Daqiang Xu
- Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou City, Jiangsu Province, 215002, China
| | - Xiaowen Gu
- Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou City, Jiangsu Province, 215002, China
| | - Zhisen Li
- Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou City, Jiangsu Province, 215002, China
| | - Yisha Zhang
- Center for Medical Ultrasound, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou City, Jiangsu Province, 215002, China
| | - Peng Wu
- Philips Healthcare, Shanghai, 200072, China
| | - Zhou Huang
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou City, Jiangsu Province, 215006, China.
| | - Jibin Zhang
- Department of Radiology, The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital, Suzhou City, Jiangsu Province, 215002, China.
| | - Yonggang Li
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou City, Jiangsu Province, 215006, China.
- Institute of Medical Imaging, Soochow University, Suzhou City, Jiangsu Province, 215000, China.
| |
Collapse
|
2
|
Cascella M, Montomoli J, Bellini V, Vittori A, Biancuzzi H, Dal Mas F, Bignami EG. Crossing the AI Chasm in Neurocritical Care. COMPUTERS 2023; 12:83. [DOI: 10.3390/computers12040083] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/12/2023]
Abstract
Despite the growing interest in possible applications of computer science and artificial intelligence (AI) in the field of neurocritical care (neuro-ICU), widespread clinical applications are still missing. In neuro-ICU, the collection and analysis in real time of large datasets can play a crucial role in advancing this medical field and improving personalized patient care. For example, AI algorithms can detect subtle changes in brain activity or vital signs, alerting clinicians to potentially life-threatening conditions and facilitating rapid intervention. Consequently, data-driven AI and predictive analytics can greatly enhance medical decision making, diagnosis, and treatment, ultimately leading to better outcomes for patients. Nevertheless, there is a significant disparity between the current capabilities of AI systems and the potential benefits and applications that could be achieved with more advanced AI technologies. This gap is usually indicated as the AI chasm. In this paper, the underlying causes of the AI chasm in neuro-ICU are analyzed, along with proposed recommendations for utilizing AI to attain a competitive edge, foster innovation, and enhance patient outcomes. To bridge the AI divide in neurocritical care, it is crucial to foster collaboration among researchers, clinicians, and policymakers, with a focus on specific use cases. Additionally, strategic investments in AI technology, education and training, and infrastructure are needed to unlock the potential of AI technology. Before implementing a technology in patient care, it is essential to conduct thorough studies and establish clinical validation in real-world environments to ensure its effectiveness and safety. Finally, the development of ethical and regulatory frameworks is mandatory to ensure the secure and efficient deployment of AI technology throughout the process.
Collapse
Affiliation(s)
- Marco Cascella
- Pain Unit and Research, Istituto Nazionale Tumori IRCCS Fondazione Pascale, 80100 Napoli, Italy
| | - Jonathan Montomoli
- Department of Anesthesia and Intensive Care, Infermi Hospital, AUSL Romagna, 47923 Rimini, Italy
| | - Valentina Bellini
- Anesthesiology, Critical Care and Pain Medicine Division, Department of Medicine and Surgery, University of Parma, 43126 Parma, Italy
| | - Alessandro Vittori
- Department of Anesthesia and Critical Care, ARCO ROMA, Ospedale Pediatrico Bambino Gesù, IRCCS, 00165 Rome, Italy
| | - Helena Biancuzzi
- Department of Economics, Ca’ Foscari University, 30121 Venice, Italy
| | - Francesca Dal Mas
- Department of Management, Ca’ Foscari University, 30121 Venice, Italy
| | - Elena Giovanna Bignami
- Anesthesiology, Critical Care and Pain Medicine Division, Department of Medicine and Surgery, University of Parma, 43126 Parma, Italy
| |
Collapse
|
3
|
Mo X, Chen X, Zeng H, Zheng W, Ieong C, Li H, Huang Q, Xu Z, Yang J, Liang Q, Liang H, Gao X, Huang M, Li J. Tacrolimus in the treatment of childhood nephrotic syndrome: Machine learning detects novel biomarkers and predicts efficacy. Pharmacotherapy 2023; 43:43-52. [PMID: 36521865 DOI: 10.1002/phar.2749] [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: 08/30/2022] [Revised: 11/10/2022] [Accepted: 11/10/2022] [Indexed: 12/23/2022]
Abstract
STUDY OBJECTIVE The pharmacokinetics and pharmacodynamics of tacrolimus (TAC) vary greatly among individuals, hindering its precise utilization. Moreover, effective models for the early prediction of TAC efficacy in patients with nephrotic syndrome (NS) are lacking. We aimed to identify key factors affecting TAC efficacy and develop efficacy prediction models for childhood NS using machine learning algorithms. DESIGN This was an observational cohort study of patients with pediatric refractory NS. SETTING Guangzhou Women and Children's Medical Center between June 2013 and December 2018. PATIENTS 203 patients with pediatric refractory NS were used for model generation and 35 patients were used for model validation. INTERVENTION All patients regularly received double immunosuppressive therapy comprising TAC and low-dose prednisone or methylprednisolone. In this observational cohort study of 203 pediatric patients with refractory NS, clinical and genetic variables, including single-nucleotide polymorphism (SNPs), were identified. TAC efficacy was evaluated 3 months after administration according to two different evaluation criteria: response or non-response (Group 1) and complete remission, partial remission, or non-remission (Group 2). MEASUREMENTS Logistic regression, extremely random trees, gradient boosting decision trees, random forest, and extreme gradient boosting algorithms were used to develop and validate the models. Prediction models were validated among a cohort of 35 patients with NS. MAIN RESULTS The random forest models performed best in both groups, and the area under the receiver operating characteristics curve of these two models was 80.7% (Group 1) and 80.3% (Group 2). These prediction models included urine erythrocyte count before administration, steroid types, and eight SNPs (ITGB4 rs2290460, TRPC6 rs3824934, CTGF rs9399005, IL13 rs20541, NFKBIA rs8904, NFKBIA rs8016947, MAP3K11 rs7946115, and SMARCAL1 rs11886806). CONCLUSIONS Two pre-administration models with good predictive performance for TAC response of patients with NS were developed and validated using machine learning algorithms. These accurate models could assist clinicians in predicting TAC efficacy in pediatric patients with NS before utilization to avoid treatment failure or adverse effects.
Collapse
Affiliation(s)
- Xiaolan Mo
- Department of Pharmacy, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China.,Institute of Clinical Pharmacology, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, China
| | - Xiujuan Chen
- Department of Medical Big Data Center, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Huasong Zeng
- Division of Nephrology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Wei Zheng
- Department of Pharmacy, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Chifong Ieong
- Institute of Clinical Pharmacology, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, China
| | - Huixian Li
- Department of Medical Big Data Center, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Qiongbo Huang
- Department of Pharmacy, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Zichuan Xu
- Division of Nephrology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Jinlian Yang
- Department of Pharmacy, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Qianying Liang
- Department of Pharmacy, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Huiying Liang
- Department of Medical Big Data Center, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
| | - Xia Gao
- Division of Nephrology, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| | - Min Huang
- Institute of Clinical Pharmacology, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, China
| | - Jiali Li
- Institute of Clinical Pharmacology, School of Pharmaceutical Sciences, Sun Yat-sen University, Guangzhou, China
| |
Collapse
|
4
|
Kim HY, Cho GJ, Kwon HS. Applications of artificial intelligence in obstetrics. Ultrasonography 2023; 42:2-9. [PMID: 36588179 PMCID: PMC9816710 DOI: 10.14366/usg.22063] [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: 04/15/2022] [Accepted: 06/20/2022] [Indexed: 01/13/2023] Open
Abstract
Artificial intelligence, which has been applied as an innovative technology in multiple fields of healthcare, analyzes large amounts of data to assist in disease prediction, prevention, and diagnosis, as well as in patient monitoring. In obstetrics, artificial intelligence has been actively applied and integrated into our daily medical practice. This review provides an overview of artificial intelligence systems currently used for obstetric diagnostic purposes, such as fetal cardiotocography, ultrasonography, and magnetic resonance imaging, and demonstrates how these methods have been developed and clinically applied.
Collapse
Affiliation(s)
- Ho Yeon Kim
- Department of Obstetrics and Gynecology, Korea University College of Medicine, Seoul, Korea
| | - Geum Joon Cho
- Department of Obstetrics and Gynecology, Korea University College of Medicine, Seoul, Korea,Correspondence to: Geum Joon Cho, MD, PhD, Department of Obstetrics and Gynecology, Korea University Guro Hospital, Korea University College of Medicine, 148 Gurodong-ro, Guro-gu, Seoul 08308, Korea Tel. +82-2-2626-3141 Fax. +82-2-838-1560 E-mail:
| | - Han Sung Kwon
- Division of Maternal and Fetal Medicine, Department of Obstetrics and Gynecology, Research Institute of Medical Science, Konkuk University School of Medicine, Seoul, Korea
| |
Collapse
|
5
|
Otjen JP, Moore MM, Romberg EK, Perez FA, Iyer RS. The current and future roles of artificial intelligence in pediatric radiology. Pediatr Radiol 2022; 52:2065-2073. [PMID: 34046708 DOI: 10.1007/s00247-021-05086-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/07/2020] [Revised: 01/27/2021] [Accepted: 04/20/2021] [Indexed: 12/11/2022]
Abstract
Artificial intelligence (AI) is a broad and complicated concept that has begun to affect many areas of medicine, perhaps none so much as radiology. While pediatric radiology has been less affected than other radiology subspecialties, there are some well-developed and some nascent applications within the field. This review focuses on the use of AI within pediatric radiology for image interpretation, with descriptive summaries of the literature to date. We highlight common features that enable successful application of the technology, along with some of the limitations that can inhibit the development of this field. We present some ideas for further research in this area and challenges that must be overcome, with an understanding that technology often advances in unpredictable ways.
Collapse
Affiliation(s)
- Jeffrey P Otjen
- Department of Radiology, Seattle Children's Hospital, University of Washington School of Medicine, 4800 Sand Point Way NE, MA.7.220, Seattle, WA, 98105, USA
| | - Michael M Moore
- Department of Radiology, Penn State Children's Hospital, Penn State Health System, Hershey, PA, USA
| | - Erin K Romberg
- Department of Radiology, Seattle Children's Hospital, University of Washington School of Medicine, 4800 Sand Point Way NE, MA.7.220, Seattle, WA, 98105, USA
| | - Francisco A Perez
- Department of Radiology, Seattle Children's Hospital, University of Washington School of Medicine, 4800 Sand Point Way NE, MA.7.220, Seattle, WA, 98105, USA
| | - Ramesh S Iyer
- Department of Radiology, Seattle Children's Hospital, University of Washington School of Medicine, 4800 Sand Point Way NE, MA.7.220, Seattle, WA, 98105, USA.
| |
Collapse
|
6
|
Hernandez NE, Lu VM, Altman N, Ragheb J, Niazi TN, Wang S. Incidence, follow-up, and postnatal clinical progress of children with central nervous system anomalies on fetal MRI. J Neurosurg Pediatr 2022; 30:160-168. [PMID: 35901770 DOI: 10.3171/2022.4.peds2269] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/23/2022] [Accepted: 04/22/2022] [Indexed: 11/06/2022]
Abstract
OBJECTIVE MRI is increasingly employed to assess intrauterine fetal anomalies. Central nervous system (CNS) anomalies are common structural conditions that warrant evaluation with fetal MRI and subsequent prenatal consultation with a pediatric neurosurgeon. As the use of fetal MRI increases, there is greater impetus to understand the most common CNS structural anomalies diagnosed in utero, as well as their natural histories. METHODS The authors performed a single-center retrospective review of fetal MRI evaluations performed between January 2012 and December 2020. Children who underwent both prenatal and postnatal neurosurgical evaluations of CNS anomalies were included. Specific CNS anomalies on fetal MRI, associated extra-CNS findings, and suspicion for genetic abnormality or syndromes were noted. Postnatal clinical status and interventions were assessed. RESULTS Between January 2012 and December 2020, a total of 469 fetal MRI evaluations were performed; of these, 114 maternal-fetal pairs had CNS anomalies that warranted prenatal consultation and postnatal pediatric neurosurgical follow-up. This cohort included 67 male infants (59%), with a mean ± SD follow-up of 29.8 ± 25.0 months after birth. Fetal MRI was performed at 27.3 ± 5.8 weeks of gestational age. The most frequently reported CNS abnormalities were ventriculomegaly (57%), agenesis or thinning of the corpus callosum (33%), Dandy-Walker complex (DWC) (21%), neuronal migration disorders (18%), and abnormalities of the septum pellucidum (17%). Twenty-one children (18%) required neurosurgical intervention at a mean age of 2.4 ± 3.7 months. The most common surgical conditions included myelomeningocele, moderate to severe ventriculomegaly, encephalocele, and arachnoid cyst. Corpus callosum agenesis or thinning was associated with developmental delay (p = 0.02) and systemic anomalies (p = 0.05). The majority of prenatal patients referred for DWC had Dandy-Walker variants that did not require surgical intervention. CONCLUSIONS The most common conditions for prenatal neurosurgical assessment were ventriculomegaly, corpus callosum anomaly, and DWC, whereas the most common surgical conditions were myelomeningocele, hydrocephalus, and arachnoid cyst. Only 18% of prenatal neurosurgical consultations resulted in surgical intervention during infancy. The majority of referrals for prenatal mild ventriculomegaly and DWC were not associated with developmental or surgical sequelae. Patients with corpus callosum abnormalities should be concurrently referred to a neurologist for developmental assessments.
Collapse
Affiliation(s)
- Nicole E Hernandez
- 1Division of Neurosurgery, Brain Institute, Nicklaus Children's Hospital, Miami, Florida
| | - Victor M Lu
- 2Department of Neurosurgery, University of Miami Miller School of Medicine, Miami, Florida; and
| | - Nolan Altman
- 3Department of Radiology, Nicklaus Children's Hospital, Miami, Florida
| | - John Ragheb
- 1Division of Neurosurgery, Brain Institute, Nicklaus Children's Hospital, Miami, Florida
- 2Department of Neurosurgery, University of Miami Miller School of Medicine, Miami, Florida; and
| | - Toba N Niazi
- 1Division of Neurosurgery, Brain Institute, Nicklaus Children's Hospital, Miami, Florida
- 2Department of Neurosurgery, University of Miami Miller School of Medicine, Miami, Florida; and
| | - Shelly Wang
- 1Division of Neurosurgery, Brain Institute, Nicklaus Children's Hospital, Miami, Florida
- 2Department of Neurosurgery, University of Miami Miller School of Medicine, Miami, Florida; and
| |
Collapse
|
7
|
Meshaka R, Gaunt T, Shelmerdine SC. Artificial intelligence applied to fetal MRI: A scoping review of current research. Br J Radiol 2022:20211205. [PMID: 35286139 DOI: 10.1259/bjr.20211205] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
Artificial intelligence (AI) is defined as the development of computer systems to perform tasks normally requiring human intelligence. A subset of AI, known as machine learning (ML), takes this further by drawing inferences from patterns in data to 'learn' and 'adapt' without explicit instructions meaning that computer systems can 'evolve' and hopefully improve without necessarily requiring external human influences. The potential for this novel technology has resulted in great interest from the medical community regarding how it can be applied in healthcare. Within radiology, the focus has mostly been for applications in oncological imaging, although new roles in other subspecialty fields are slowly emerging.In this scoping review, we performed a literature search of the current state-of-the-art and emerging trends for the use of artificial intelligence as applied to fetal magnetic resonance imaging (MRI). Our search yielded several publications covering AI tools for anatomical organ segmentation, improved imaging sequences and aiding in diagnostic applications such as automated biometric fetal measurements and the detection of congenital and acquired abnormalities. We highlight our own perceived gaps in this literature and suggest future avenues for further research. It is our hope that the information presented highlights the varied ways and potential that novel digital technology could make an impact to future clinical practice with regards to fetal MRI.
Collapse
Affiliation(s)
- Riwa Meshaka
- Department of Clinical Radiology, Great Ormond Street Hospital for Children NHS Foundation Trust, Great Ormond Street, London, UK
| | - Trevor Gaunt
- Department of Radiology, University College London Hospitals NHS Foundation Trust, London, UK
| | - Susan C Shelmerdine
- Department of Clinical Radiology, Great Ormond Street Hospital for Children NHS Foundation Trust, Great Ormond Street, London, UK.,UCL Great Ormond Street Institute of Child Health, Great Ormond Street Hospital for Children, London, UK.,NIHR Great Ormond Street Hospital Biomedical Research Centre, 30 Guilford Street, Bloomsbury, London, UK.,Department of Radiology, St. George's Hospital, Blackshaw Road, London, UK
| |
Collapse
|
8
|
Dagi TF, Barker FG, Glass J. Machine Learning and Artificial Intelligence in Neurosurgery: Status, Prospects, and Challenges. Neurosurgery 2021; 89:133-142. [PMID: 34015816 DOI: 10.1093/neuros/nyab170] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/06/2023] Open
Affiliation(s)
- T Forcht Dagi
- Queen's University Belfast and The William J. Clinton Leadership Institute, Belfast, UK
- Mayo Clinic College of Medicine and Science, Rochester, Minnesota, USA
| | - Fred G Barker
- Department of Neurosurgery, Harvard Medical School, Boston, Massachusetts, USA
- The Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Jacob Glass
- Center for Epigenetics Research, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| |
Collapse
|
9
|
Hale AT, Riva-Cambrin J, Wellons JC, Jackson EM, Kestle JRW, Naftel RP, Hankinson TC, Shannon CN. Machine learning predicts risk of cerebrospinal fluid shunt failure in children: a study from the hydrocephalus clinical research network. Childs Nerv Syst 2021; 37:1485-1494. [PMID: 33515058 DOI: 10.1007/s00381-021-05061-7] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/05/2021] [Accepted: 01/22/2021] [Indexed: 10/22/2022]
Abstract
PURPOSE While conventional statistical approaches have been used to identify risk factors for cerebrospinal fluid (CSF) shunt failure, these methods may not fully capture the complex contribution of clinical, radiologic, surgical, and shunt-specific variables influencing this outcome. Using prospectively collected data from the Hydrocephalus Clinical Research Network (HCRN) patient registry, we applied machine learning (ML) approaches to create a predictive model of CSF shunt failure. METHODS Pediatric patients (age < 19 years) undergoing first-time CSF shunt placement at six HCRN centers were included. CSF shunt failure was defined as a composite outcome including requirement for shunt revision, endoscopic third ventriculostomy, or shunt infection within 5 years of initial surgery. Performance of conventional statistical and 4 ML models were compared. RESULTS Our cohort consisted of 1036 children undergoing CSF shunt placement, of whom 344 (33.2%) experienced shunt failure. Thirty-eight clinical, radiologic, surgical, and shunt-design variables were included in the ML analyses. Of all ML algorithms tested, the artificial neural network (ANN) had the strongest performance with an area under the receiver operator curve (AUC) of 0.71. The ANN had a specificity of 90% and a sensitivity of 68%, meaning that the ANN can effectively rule-in patients most likely to experience CSF shunt failure (i.e., high specificity) and moderately effective as a tool to rule-out patients at high risk of CSF shunt failure (i.e., moderately sensitive). The ANN was independently validated in 155 patients (prospectively collected, retrospectively analyzed). CONCLUSION These data suggest that the ANN, or future iterations thereof, can provide an evidence-based tool to assist in prognostication and patient-counseling immediately after CSF shunt placement.
Collapse
Affiliation(s)
- Andrew T Hale
- Medical Scientist Training Program, Vanderbilt University School of Medicine, 2200 Pierce Ave., Light Hall 514, Nashville, TN, 37232, USA. .,Surgical Outcomes Center for Kids, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA.
| | - Jay Riva-Cambrin
- Department of Clinical Neurosciences, Alberta Children's Hospital, University of Calgary, Calgary, Alberta, Canada
| | - John C Wellons
- Surgical Outcomes Center for Kids, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA.,Division of Pediatric Neurosurgery, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA
| | - Eric M Jackson
- Department of Neurosurgery, Johns Hopkins Children's Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - John R W Kestle
- Department of Neurosurgery, University of Utah, Salt Lake City, UT, USA
| | - Robert P Naftel
- Surgical Outcomes Center for Kids, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA.,Division of Pediatric Neurosurgery, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA
| | - Todd C Hankinson
- Division of Pediatric Neurosurgery, Children's Hospital Colorado, Aurora, CO, USA
| | - Chevis N Shannon
- Surgical Outcomes Center for Kids, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA.,Division of Pediatric Neurosurgery, Monroe Carell Jr. Children's Hospital of Vanderbilt University, Nashville, TN, USA
| | | |
Collapse
|
10
|
Quon JL, Jin MC, Seekins J, Yeom KW. Harnessing the potential of artificial neural networks for pediatric patient management. Artif Intell Med 2021. [DOI: 10.1016/b978-0-12-821259-2.00021-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/23/2022]
|
11
|
Kedia S, Pahwa B, Bali O, Goyal S. Applications of Machine Learning in Pediatric Hydrocephalus: A Systematic Review. Neurol India 2021; 69:S380-S389. [DOI: 10.4103/0028-3886.332287] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
|
12
|
Li QM, Liao HZ, Wang WB, Zeng SY, Qiu XS, Ke S, Xiao J, Li QH, Xia XW, Li Y. Prognostic Analysis and Risk Factors Associated with Fetal Ventriculomegaly. Pediatr Neurosurg 2021; 56:407-415. [PMID: 34175844 DOI: 10.1159/000516378] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/11/2020] [Accepted: 04/04/2021] [Indexed: 11/19/2022]
Abstract
BACKGROUND This study aimed to investigate the clinical outcome and related risk factors of fetal lateral ventriculomegaly (VM). METHODS A retrospective analysis was performed on 255 cases diagnosed as fetal VM. Prenatal imaging examination was carried out. The pregnancy outcomes were investigated through follow-up. According to the prognosis of children, they were divided into case group and control group. Multivariate logistic regression was used to analyze the factors influencing the prognosis of hydrocephalus. RESULTS After excluding the cases with either loss of follow-up or incomplete information, 102 cases were followed up. Twelve cases with poor prognosis were set as the case group. According to the maternal age, gestational age, gender of children, and follow-up time, 3 cases were selected from the other 90 cases for each child in the case group, respectively, and selected as the control group. Paired comparative analysis was performed on 48 cases. Using prognosis as a dependent variable, multivariate logistic regression analysis of the statistically significant factors indicated that the change speed of width ratio (CSWR) and maximum lateral ventricular width (MW) were associated with fetal prognosis. CONCLUSIONS Our results suggested that CSWR and MW may have the value of predicting fetal prognosis.
Collapse
Affiliation(s)
- Qi-Ming Li
- Department of Neurosurgery, Taihe Hospital, Shiyan, China, .,Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China,
| | - Hong-Zhan Liao
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Wen-Bo Wang
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Shi-Yi Zeng
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Xian-Sheng Qiu
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Shuai Ke
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Jing Xiao
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Qing-Hua Li
- Department of Neurology, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Xue-Wei Xia
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China
| | - Yong Li
- Department of Neurosurgery, Affiliated Hospital of Guilin Medical University, Guilin, China.,Sport and Health College of Guangxi Normal University, Guilin, China
| |
Collapse
|
13
|
Chaudhry F, Hunt RJ, Hariharan P, Anand SK, Sanjay S, Kjoller EE, Bartlett CM, Johnson KW, Levy PD, Noushmehr H, Lee IY. Machine Learning Applications in the Neuro ICU: A Solution to Big Data Mayhem? Front Neurol 2020; 11:554633. [PMID: 33162926 PMCID: PMC7581704 DOI: 10.3389/fneur.2020.554633] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2020] [Accepted: 09/09/2020] [Indexed: 12/21/2022] Open
Abstract
The neurological ICU (neuro ICU) often suffers from significant limitations due to scarce resource availability for their neurocritical care patients. Neuro ICU patients require frequent neurological evaluations, continuous monitoring of various physiological parameters, frequent imaging, and routine lab testing. This amasses large amounts of data specific to each patient. Neuro ICU teams are often overburdened by the resulting complexity of data for each patient. Machine Learning algorithms (ML), are uniquely capable of interpreting high-dimensional datasets that are too difficult for humans to comprehend. Therefore, the application of ML in the neuro ICU could alleviate the burden of analyzing big datasets for each patient. This review serves to (1) briefly summarize ML and compare the different types of MLs, (2) review recent ML applications to improve neuro ICU management and (3) describe the future implications of ML to neuro ICU management.
Collapse
Affiliation(s)
- Farhan Chaudhry
- Department of Emergency Medicine and Integrative Biosciences Center, Wayne State University, Detroit, MI, United States
- Department of Neurosurgery, Henry Ford Hospital, Detroit, MI, United States
| | - Rachel J. Hunt
- Department of Neurosurgery, Henry Ford Hospital, Detroit, MI, United States
| | - Prashant Hariharan
- Department of Biomedical Engineering, Wayne State University, Detroit, MI, United States
| | - Sharath Kumar Anand
- Department of Emergency Medicine and Integrative Biosciences Center, Wayne State University, Detroit, MI, United States
| | - Surya Sanjay
- Department of Emergency Medicine and Integrative Biosciences Center, Wayne State University, Detroit, MI, United States
| | - Ellen E. Kjoller
- Department of Emergency Medicine and Integrative Biosciences Center, Wayne State University, Detroit, MI, United States
| | - Connor M. Bartlett
- Department of Emergency Medicine and Integrative Biosciences Center, Wayne State University, Detroit, MI, United States
| | - Kipp W. Johnson
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States
| | - Phillip D. Levy
- Department of Emergency Medicine and Integrative Biosciences Center, Wayne State University, Detroit, MI, United States
| | - Houtan Noushmehr
- Department of Neurosurgery, Henry Ford Hospital, Detroit, MI, United States
| | - Ian Y. Lee
- Department of Neurosurgery, Henry Ford Hospital, Detroit, MI, United States
| |
Collapse
|
14
|
Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty. Neuroimage 2020; 223:117316. [PMID: 32890745 DOI: 10.1016/j.neuroimage.2020.117316] [Citation(s) in RCA: 24] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Revised: 07/25/2020] [Accepted: 08/24/2020] [Indexed: 12/30/2022] Open
Abstract
MRI-based brain age prediction has been widely used to characterize normal brain development, and deviations from the typical developmental trajectory are indications of brain abnormalities. Age prediction of the fetal brain remains unexplored, although it can be of broad interest to prenatal examination given the limited diagnostic tools available for assessment of the fetal brain. In this work, we built an attention-based deep residual network based on routine clinical T2-weighted MR images of 659 fetal brains, which achieved an overall mean absolute error of 0.767 weeks and R2 of 0.920 in fetal brain age prediction. The predictive uncertainty and estimation confidence were simultaneously quantified from the network as markers for detecting fetal brain anomalies using an ensemble method. The novel markers overcame the limitations in conventional brain age estimation and demonstrated promising diagnostic power in differentiating several types of fetal abnormalities, including small head circumference, malformations and ventriculomegaly with the area under the curve of 0.90, 0.90 and 0.67, respectively. In addition, attention maps were derived from the network, which revealed regional features that contributed to fetal age estimation at each gestational stage. The proposed attention-based deep ensembles demonstrated superior performance in fetal brain age estimation and fetal anomaly detection, which has the potential to be translated to prenatal diagnosis in clinical practice.
Collapse
|
15
|
Bennett TD, Callahan TJ, Feinstein JA, Ghosh D, Lakhani SA, Spaeder MC, Szefler SJ, Kahn MG. Data Science for Child Health. J Pediatr 2019; 208:12-22. [PMID: 30686480 PMCID: PMC6486872 DOI: 10.1016/j.jpeds.2018.12.041] [Citation(s) in RCA: 20] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/22/2018] [Revised: 12/11/2018] [Accepted: 12/18/2018] [Indexed: 12/12/2022]
Affiliation(s)
- Tellen D Bennett
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO; CU Data Science to Patient Value (D2V), University of Colorado School of Medicine, Aurora, CO; Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO; Adult and Child Consortium for Outcomes Research and Delivery Science (ACCORDS), University of Colorado School of Medicine and Children's Hospital Colorado, Aurora, CO; Computational Bioscience Program, University of Colorado Denver Anschutz Medical Campus, Aurora, CO.
| | - Tiffany J Callahan
- Computational Bioscience Program, University of Colorado Denver Anschutz Medical Campus, Aurora, CO
| | - James A Feinstein
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO; Adult and Child Consortium for Outcomes Research and Delivery Science (ACCORDS), University of Colorado School of Medicine and Children's Hospital Colorado, Aurora, CO
| | - Debashis Ghosh
- CU Data Science to Patient Value (D2V), University of Colorado School of Medicine, Aurora, CO; Biostatistics and Informatics, Colorado School of Public Health, Aurora, CO; Computational Bioscience Program, University of Colorado Denver Anschutz Medical Campus, Aurora, CO
| | - Saquib A Lakhani
- Pediatric Genomics Discovery Program, Department of Pediatrics, Yale University School of Medicine, New Haven, CT
| | - Michael C Spaeder
- Pediatric Critical Care, University of Virginia School of Medicine, Charlottesville, VA
| | - Stanley J Szefler
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO; Adult and Child Consortium for Outcomes Research and Delivery Science (ACCORDS), University of Colorado School of Medicine and Children's Hospital Colorado, Aurora, CO
| | - Michael G Kahn
- Department of Pediatrics, University of Colorado School of Medicine, Aurora, CO; Computational Bioscience Program, University of Colorado Denver Anschutz Medical Campus, Aurora, CO
| |
Collapse
|