RESUMEN
Big data has transformed into a trend phrase in healthcare and neurosurgery, becoming a pervasive and inescapable phrase in everyday life. The upsurge in big data applications is a direct consequence of the drastic boom in information technology as well as the growing number of internet-connected devices called the Internet of Things in healthcare. Compared with business, marketing, and other sectors, healthcare applications are lagging due to a lack of technical knowledge among healthcare workers, technological limitations in acquiring and analyzing the data, and improper governance of healthcare big data. Despite these limitations, the medical literature is flooded with big data-related articles, and most of these are filled with abstruse terminologies such as machine learning, artificial intelligence, artificial neural network, and algorithm. Many of the recent articles are restricted to neurosurgical registries, creating a false impression that big data is synonymous with registries. Others advocate that the utilization of big data will be the panacea to all healthcare problems and research in the future. Without a proper understanding of these principles, it becomes easy to get lost without the ability to differentiate hype from reality. To that end, the authors give a brief narrative of big data analysis in neurosurgery and review its applications, limitations, and the challenges it presents for neurosurgeons and healthcare professionals naive to this field. Awareness of these basic concepts will allow neurosurgeons to understand the literature regarding big data, enabling them to make better decisions and deliver personalized care.
RESUMEN
OBJECTIVE: Surgical site infection (SSI) following a neurosurgical operation is a complication that impacts morbidity, mortality, and economics. Currently, machine learning (ML) algorithms are used for outcome prediction in various neurosurgical aspects. The implementation of ML algorithms to learn from medical data may help in obtaining prognostic information on diseases, especially SSIs. The purpose of this study was to compare the performance of various ML models for predicting surgical infection after neurosurgical operations. METHODS: A retrospective cohort study was conducted on patients who had undergone neurosurgical operations at tertiary care hospitals between 2010 and 2017. Supervised ML algorithms, which included decision tree, naive Bayes with Laplace correction, k-nearest neighbors, and artificial neural networks, were trained and tested as binary classifiers (infection or no infection). To evaluate the ML models from the testing data set, their sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), as well as their accuracy, receiver operating characteristic curve, and area under the receiver operating characteristic curve (AUC) were analyzed. RESULTS: Data were available for 1471 patients in the study period. The SSI rate was 4.6%, and the type of SSI was superficial, deep, and organ/space in 1.2%, 0.8%, and 2.6% of cases, respectively. Using the backward stepwise method, the authors determined that the significant predictors of SSI in the multivariable Cox regression analysis were postoperative CSF leakage/subgaleal collection (HR 4.24, p < 0.001) and postoperative fever (HR 1.67, p = 0.04). Compared with other ML algorithms, the naive Bayes had the highest performance with sensitivity at 63%, specificity at 87%, PPV at 29%, NPV at 96%, and AUC at 76%. CONCLUSIONS: The naive Bayes algorithm is highlighted as an accurate ML method for predicting SSI after neurosurgical operations because of its reasonable accuracy. Thus, it can be used to effectively predict SSI in individual neurosurgical patients. Therefore, close monitoring and allocation of treatment strategies can be informed by ML predictions in general practice.
Asunto(s)
Aprendizaje Automático , Neurocirugia , Procedimientos Neuroquirúrgicos/efectos adversos , Infección de la Herida Quirúrgica/cirugía , Adulto , Anciano , Femenino , Humanos , Masculino , Persona de Mediana Edad , Neurocirugia/métodos , Curva ROC , Estudios Retrospectivos , Factores de Riesgo , Infección de la Herida Quirúrgica/etiologíaRESUMEN
OBJECTIVE: Nonhome discharge and unplanned readmissions represent important cost drivers following spinal fusion. The authors sought to utilize different machine learning algorithms to predict discharge to rehabilitation and unplanned readmissions in patients receiving spinal fusion. METHODS: The authors queried the 2012-2013 American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) for patients undergoing cervical or lumbar spinal fusion. Outcomes assessed included discharge to nonhome facility and unplanned readmissions within 30 days after surgery. A total of 7 machine learning algorithms were evaluated. Predictive hierarchical clustering of procedure codes was used to increase model performance. Model performance was evaluated using overall accuracy and area under the receiver operating characteristic curve (AUC), as well as sensitivity, specificity, and positive and negative predictive values. These performance metrics were computed for both the imputed and unimputed (missing values dropped) datasets. RESULTS: A total of 59,145 spinal fusion cases were analyzed. The incidence rates of discharge to nonhome facility and 30-day unplanned readmission were 12.6% and 4.5%, respectively. All classification algorithms showed excellent discrimination (AUC > 0.80, range 0.85-0.87) for predicting nonhome discharge. The generalized linear model showed comparable performance to other machine learning algorithms. By comparison, all models showed poorer predictive performance for unplanned readmission, with AUC ranging between 0.63 and 0.66. Better predictive performance was noted with models using imputed data. CONCLUSIONS: In an analysis of patients undergoing spinal fusion, multiple machine learning algorithms were found to reliably predict nonhome discharge with modest performance noted for unplanned readmissions. These results provide early evidence regarding the feasibility of modern machine learning classifiers in predicting these outcomes and serve as possible clinical decision support tools to facilitate shared decision making.
RESUMEN
OBJECTIVEArtificial neural networks (ANNs) have shown considerable promise as decision support tools in medicine, including neurosurgery. However, their use in concussion and postconcussion syndrome (PCS) has been limited. The authors explore the value of using an ANN to identify patients with concussion/PCS based on their antisaccade performance.METHODSStudy participants were prospectively recruited from the emergency department and head injury clinic of a large teaching hospital in Toronto. Acquaintances of study participants were used as controls. Saccades were measured using an automated, portable, head-mounted device preprogrammed with an antisaccade task. Each participant underwent 100 trials of the task and 11 saccade parameters were recorded for each trial. ANN analysis was performed using the MATLAB Neural Network Toolbox, and individual saccade parameters were further explored with receiver operating characteristic (ROC) curves and a logistic regression analysis.RESULTSControl (n = 15), concussion (n = 32), and PCS (n = 25) groups were matched by age and level of education. The authors examined 11 saccade parameters and found that the prosaccade error rate (p = 0.04) and median antisaccade latency (p = 0.02) were significantly different between control and concussion/PCS groups. When used to distinguish concussion and PCS participants from controls, the neural networks achieved accuracies of 67% and 72%, respectively. This method was unable to distinguish study patients with concussion from those with PCS, suggesting persistence of eye movement abnormalities in patients with PCS. The authors' observations also suggest the potential for improved results with a larger training sample.CONCLUSIONSThis study explored the utility of ANNs in the diagnosis of concussion/PCS based on antisaccades. With the use of an ANN, modest accuracy was achieved in a small cohort. In addition, the authors explored the pearls and pitfalls of this novel approach and identified important future directions for this research.
RESUMEN
In BriefPediatric traumatic brain injury (TBI) is common, but not all injuries require hospitalization. A computational tool for ruling-in patients who will have clinically relevant TBI (CRTBI) would be valuable, providing an evidence-based mechanism for safe discharge. Here, using data from 12,902 patients from the Pediatric Emergency Care Applied Research Network (PECARN) TBI data set, the authors utilize artificial intelligence to predict CRTBI using radiologist-interpreted CT information with > 99% sensitivity and an AUC of 0.99.
Asunto(s)
Lesiones Traumáticas del Encéfalo/diagnóstico , Redes Neurales de la Computación , Tomografía Computarizada por Rayos X , Adolescente , Algoritmos , Área Bajo la Curva , Lesiones Traumáticas del Encéfalo/diagnóstico por imagen , Lesiones Traumáticas del Encéfalo/etiología , Niño , Reacciones Falso Positivas , Femenino , Humanos , Masculino , Valor Predictivo de las Pruebas , Sensibilidad y EspecificidadRESUMEN
OBJECTIVEModern surgical planning and prognostication requires the most accurate outcomes data to practice evidence-based medicine. For clinicians treating children following traumatic brain injury (TBI) these data are severely lacking. The first aim of this study was to assess published CT classification systems in the authors' pediatric cohort. A pediatric-specific machine-learning algorithm called an artificial neural network (ANN) was then created that robustly outperformed traditional CT classification systems in predicting TBI outcomes in children.METHODSThe clinical records of children under the age of 18 who suffered a TBI and underwent head CT within 24 hours after TBI (n = 565) were retrospectively reviewed.RESULTS"Favorable" outcome (alive with Glasgow Outcome Scale [GOS] score ≥ 4 at 6 months postinjury, n = 533) and "unfavorable" outcome (death at 6 months or GOS score ≤ 3 at 6 months postinjury, n = 32) were used as the primary outcomes. The area under the receiver operating characteristic (ROC) curve (AUC) was used to delineate the strength of each CT grading system in predicting survival (Helsinki, 0.814; Rotterdam, 0.838; and Marshall, 0.781). The AUC for CT score in predicting GOS score ≤ 3, a measure of overall functionality, was similarly predictive (Helsinki, 0.717; Rotterdam, 0.748; and Marshall, 0.663). An ANN was then constructed that was able to predict 6-month outcomes with profound accuracy (AUC = 0.9462 ± 0.0422).CONCLUSIONSThis study showed that machine-learning can be leveraged to more accurately predict TBI outcomes in children.
Asunto(s)
Lesiones Traumáticas del Encéfalo/clasificación , Lesiones Traumáticas del Encéfalo/diagnóstico , Registros Electrónicos de Salud/clasificación , Clasificación Internacional de Enfermedades , Aprendizaje Automático/clasificación , Modelos Estadísticos , Adolescente , Niño , Preescolar , Registros Electrónicos de Salud/normas , Registros Electrónicos de Salud/tendencias , Femenino , Humanos , Lactante , Recién Nacido , Clasificación Internacional de Enfermedades/normas , Clasificación Internacional de Enfermedades/tendencias , Aprendizaje Automático/normas , Masculino , Factores de Tiempo , Resultado del TratamientoRESUMEN
OBJECTIVEPrognostication and surgical planning for WHO grade I versus grade II meningioma requires thoughtful decision-making based on radiographic evidence, among other factors. Although conventional statistical models such as logistic regression are useful, machine learning (ML) algorithms are often more predictive, have higher discriminative ability, and can learn from new data. The authors used conventional statistical models and an array of ML algorithms to predict atypical meningioma based on radiologist-interpreted preoperative MRI findings. The goal of this study was to compare the performance of ML algorithms to standard statistical methods when predicting meningioma grade.METHODSThe cohort included patients aged 18-65 years with WHO grade I (n = 94) and II (n = 34) meningioma in whom preoperative MRI was obtained between 1998 and 2010. A board-certified neuroradiologist, blinded to histological grade, interpreted all MR images for tumor volume, degree of peritumoral edema, presence of necrosis, tumor location, presence of a draining vein, and patient sex. The authors trained and validated several binary classifiers: k-nearest neighbors models, support vector machines, naïve Bayes classifiers, and artificial neural networks as well as logistic regression models to predict tumor grade. The area under the curve-receiver operating characteristic curve was used for comparison across and within model classes. All analyses were performed in MATLAB using a MacBook Pro.RESULTSThe authors included 6 preoperative imaging and demographic variables: tumor volume, degree of peritumoral edema, presence of necrosis, tumor location, patient sex, and presence of a draining vein to construct the models. The artificial neural networks outperformed all other ML models across the true-positive versus false-positive (receiver operating characteristic) space (area under curve = 0.8895).CONCLUSIONSML algorithms are powerful computational tools that can predict meningioma grade with great accuracy.
Asunto(s)
Aprendizaje Automático , Imagen por Resonancia Magnética/métodos , Neoplasias Meníngeas/diagnóstico por imagen , Meningioma/diagnóstico por imagen , Adulto , Estudios de Cohortes , Femenino , Humanos , Aprendizaje Automático/normas , Imagen por Resonancia Magnética/normas , Masculino , Persona de Mediana Edad , Clasificación del Tumor/métodos , Clasificación del Tumor/normas , Estudios RetrospectivosRESUMEN
OBJECTIVE Carotid artery stenting (CAS) has been considered to prevent ischemic strokes caused by stenosis of the cervical carotid artery. The most common complication of CAS is new cerebral infarction. The authors have previously reported that the jellyfish sign-the rise and fall of the mobile component of the carotid plaque surface detected by carotid ultrasonography-suggests thinning and rupture of the fibrous cap over the unstable plaque content, such as the lipid-rich necrotic core or internal plaque hemorrhage. The authors' aim in the present study was to evaluate the risk of a new ischemic lesion after CAS by using many risk factors including calcification (size and location) and the jellyfish sign. METHODS Eighty-six lesions (77 patients) were treated with CAS. The presence of ischemic stroke was determined using diffusion-weighted imaging (DWI). Risk factors included calcification of the plaque (classified into 5 groups for size and 3 groups for location) and the jellyfish sign, among others. Multiple linear regression analysis (stepwise analysis and partial least squares [PLS] analysis) was conducted, followed by a machine learning analysis using an artificial neural network (ANN) based on the log-linearized gaussian mixture network (LLGMN). The additive effects of the jellyfish sign and calcification on ischemic stroke after CAS were examined using the Kruskal-Wallis test, followed by the Steel-Dwass test. RESULTS The stepwise analysis selected the jellyfish sign, proximal calcification (proximal Ca), low-density lipoprotein (LDL) cholesterol, and patient age for the prediction model to predict new DWI lesions. The PLS analysis revealed the same top 3 variables (jellyfish sign, proximal Ca, and LDL cholesterol) according to the variable importance in projection scores. The ANN was then used, showing that these 3 variables remained. The accuracy of the ANN improved; areas under the receiver operating characteristic curves of the stepwise analysis, the PLS analysis, and the ANN were 0.719, 0.727, and 0.768, respectively. The combination of the jellyfish sign and proximal Ca indicates a significantly increased risk for ischemic stroke after CAS. CONCLUSIONS The jellyfish sign, proximal Ca, and LDL cholesterol were considered to be important predictors for new DWI lesions after CAS. These 3 factors can be easily determined during a standard clinical visit. Thus, these 3 variables-especially the jellyfish sign and proximal Ca-may be useful for reducing the ischemic stroke risk in patients with stenosis of the cervical carotid artery.
Asunto(s)
Isquemia Encefálica/diagnóstico , Calcinosis/cirugía , Estenosis Carotídea/cirugía , Complicaciones Posoperatorias/diagnóstico , Stents , Accidente Cerebrovascular/diagnóstico , Factores de Edad , Anciano , Anciano de 80 o más Años , Isquemia Encefálica/epidemiología , Isquemia Encefálica/etiología , Calcinosis/diagnóstico por imagen , Calcinosis/epidemiología , Arterias Carótidas/diagnóstico por imagen , Arterias Carótidas/cirugía , Estenosis Carotídea/diagnóstico por imagen , Estenosis Carotídea/epidemiología , LDL-Colesterol/sangre , Imagen de Difusión por Resonancia Magnética , Femenino , Humanos , Interpretación de Imagen Asistida por Computador/métodos , Masculino , Persona de Mediana Edad , Complicaciones Posoperatorias/epidemiología , Complicaciones Posoperatorias/etiología , Pronóstico , Factores de Riesgo , Accidente Cerebrovascular/epidemiología , Accidente Cerebrovascular/etiología , UltrasonografíaRESUMEN
OBJECTIVE The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS Five hundred fifty-seven patients were included: 409 (73.4%) in the NOCOMP group, and 148 (26.6%) in the COMP group. The overall model accuracy was 87.6% correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS A successful model (87% accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.