Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 31
Filtrar
1.
Acta Neurochir (Wien) ; 165(9): 2597-2604, 2023 09.
Artículo en Inglés | MEDLINE | ID: mdl-37587319

RESUMEN

BACKGROUND: There is a strong need for the development of core outcome sets (COS) across nerve surgery to allow for improved data synthesis, meta-analyses, and reporting consistency. Development of a core outcome set typically starts with assessing the literature for previously reported outcome measures. Common peroneal neuropathy (CPN) is the most common compressive mononeuropathy of the lower extremity and can result in pain, motor, and sensory deficits. A COS for COmmon PEroneal neuropathy (COS-COPE) is needed to improve future study design and comparison and synthesis of data. The goal of the current study was to assess the literature for outcomes reported in studies on CPN as the first step in the development of a COS. METHODS: A systematic review of the literature from 2000 to 2023 was performed utilizing PubMed and Medical Subject Headings (MeSH). Identified articles were screened according to study inclusion/exclusion criteria. Outcome measures reported in each included study were recorded and categorized into motor, sensory, pain, composite foot/ankle score, electrodiagnostics, function/disability patient-reported outcome (PRO), psychological, or other outcomes. Descriptive statistics were performed. RESULTS: A total of 31 articles met criteria for inclusion. A motor outcome was reported in 26 (83.9%) studies; 12 (38.7%) reported a sensory outcome; 8 (25.8%) reported a pain outcome; 4 (12.9%) reported a composite foot/ankle score; 3 (9.7%) reported electrodiagnostics; 1 (3.2%) reported a function/disability PRO; 1 (3.2%) reported a psychological outcome; 2 (6.5%) reported an imaging outcome; 3 (9.7%) reported other outcomes. Across the studies, 29 distinct outcome measures were reported. CONCLUSIONS: The outcomes reported in studies on CPN are varied and inconsistent. It is likely that a combination of motor, sensory, pain, and functional outcomes will be needed in a COS to best study CPN. These data will serve as a baseline for the ultimate development of the COS-COPE.


Asunto(s)
Neuropatías Peroneas , Humanos , Neuropatías Peroneas/diagnóstico , Neuropatías Peroneas/cirugía , Extremidad Inferior , Procedimientos Neuroquirúrgicos , Dolor , Medición de Resultados Informados por el Paciente
2.
Neurosurgery ; 94(1): 193-201, 2024 01 01.
Artículo en Inglés | MEDLINE | ID: mdl-37850933

RESUMEN

BACKGROUND AND OBJECTIVES: There is a relative dearth of published data with respect to recovery of upper extremity movement after nerve reconstruction for neonatal brachial plexus palsy (NBPP). This study aimed to demonstrate long-term recovery of active range of motion (AROM) at the shoulder, elbow, and forearm after nerve reconstruction for NBPP and to compare that with patients managed nonoperatively. METHODS: We interrogated a prospectively collected database of all patients evaluated for NBPP at a single institution from 2005 to 2020. AROM measurements for shoulder, elbow, and forearm movements were collected at every visit up to 5 years of follow-up and normalized between 0 and 1. We used generalized estimated equations to predict AROM for each movement within local age windows over 5 years and compared the operative and nonoperative cohorts at each age interval. RESULTS: In total, >13 000 collected datapoints representing 425 conservatively and 99 operatively managed children were included for analysis. At 5 years, absolute recovery of AROM after nerve reconstruction was ∼50% for shoulder abduction and forward flexion, ∼65% for shoulder external rotation, and ∼75% for elbow flexion and forearm supination, with ∼20% loss of elbow extension AROM. Despite more limited AROM on presentation for the operative cohort, at 5 years, there was no significant difference between the groups in AROM for shoulder external rotation, elbow extension, or forearm supination, and, in Narakas grade 1-2 injury, shoulder abduction and forward flexion. CONCLUSION: We demonstrate recovery of upper extremity AROM after nerve surgery for NBPP. Despite more severe presenting injury, operative patients had similar recovery of AROM when compared with nonoperative patients for shoulder external rotation, elbow extension, forearm supination, and, for Narakas grade 1-2 injury, shoulder abduction and forward flexion.


Asunto(s)
Neuropatías del Plexo Braquial , Parálisis Neonatal del Plexo Braquial , Transferencia de Nervios , Lesiones del Hombro , Recién Nacido , Niño , Humanos , Preescolar , Parálisis Neonatal del Plexo Braquial/cirugía , Antebrazo/cirugía , Hombro , Codo/cirugía , Neuropatías del Plexo Braquial/cirugía , Extremidad Superior , Rango del Movimiento Articular/fisiología , Lesiones del Hombro/cirugía , Transferencia de Nervios/métodos , Resultado del Tratamiento
3.
Neurosurgery ; 94(3): 552-558, 2024 Mar 01.
Artículo en Inglés | MEDLINE | ID: mdl-37732746

RESUMEN

BACKGROUND AND OBJECTIVES: Determining functional recovery in adult patients with traumatic pan-brachial plexus injury (pBPI) is hampered by the fact that most outcome measures are collected in the clinical setting and may not reflect arm use in the real world. This study's objectives were to demonstrate the feasibility of using wearable motion sensor technology to quantify spontaneous arm movement in adult patients with pBPI after surgical reconstruction and report the time and intensity with which the affected arm was used. METHODS: Twenty-nine patients with pBPI who underwent surgical reconstruction at least 2 years prior were included in this study. Study participants wore an accelerometer on bilateral arms for 7 days. The vector time (VT) and magnitude with which each arm moved were collected and divided by the same values collected from the uninjured arm to generate a ratio (VT and vector magnitude [VM], respectively) to quantify differences between the arms. Correlations between VT, VM, and patient demographic and physician-elicited clinical measures were calculated. Patients were enrolled at Chang Gung Memorial Hospital, Linkou Medical Center, Taiwan, and data analysis was performed at the University of Michigan. RESULTS: Twelve patients had pan-avulsion injuries, and 17 patients had C5 rupture with C6-T1 avulsion injuries. All underwent nerve reconstruction with contralateral C7 or ipsilateral C5 nerve roots as donors. At mean 7.3 years after surgery, the mean VT ratio was 0.54 ± 0.13 and the mean VM ratio was 0.30 ± 0.13. Both VT and VM ratios were significantly correlated with patient employment and movements at the elbow and forearm. CONCLUSION: Wearable motion detection technology can capture spontaneous, real-world movements of the arm in patients who have undergone surgical reconstruction for pBPI. Despite severe injuries, these patients are able to use their affected arm 50% of the time and with 30% of the intensity of their unaffected arm, which is positively correlated with return to work after injury. These data support the use of surgical reconstruction for pBPI.


Asunto(s)
Neuropatías del Plexo Braquial , Plexo Braquial , Transferencia de Nervios , Adulto , Humanos , Neuropatías del Plexo Braquial/cirugía , Plexo Braquial/cirugía , Plexo Braquial/lesiones , Extremidad Superior/cirugía , Brazo , Resultado del Tratamiento
4.
Neurosurg Focus Video ; 8(1): V2, 2023 Jan.
Artículo en Inglés | MEDLINE | ID: mdl-36628096

RESUMEN

Neonatal brachial plexus palsy describes injury to the brachial plexus in the perinatal period, resulting in motor and sensory deficits of the upper arm. Nerve reconstruction, including graft repair and nerve transfers, can be used to restore function in patients whose injury does not respond to conservative management. Despite the availability of these techniques, 30%-40% of children have lifelong disability, reflecting a 10-fold underutilization of surgery. Here, the authors demonstrate a supraclavicular approach for brachial plexus exploration, as well as a spinal accessory to suprascapular nerve transfer for restoration of shoulder abduction and external rotation. The video can be found here: https://stream.cadmore.media/r10.3171/2022.10.FOCVID22109.

5.
J Neurosurg ; 139(6): 1552-1559, 2023 12 01.
Artículo en Inglés | MEDLINE | ID: mdl-37178028

RESUMEN

The highest-impact medical literature is increasingly produced by interdisciplinary teams. The field of neurosurgery, which involves complex pathologies and recoveries, is particularly amenable to interdisciplinary research approaches. However, research in the medical context regarding the characteristics of effective teams, as well as how to develop and maintain interdisciplinary teams, remains lacking. Here, the authors used the business literature to identify the characteristics of effective teams. They then used the University of Michigan Brachial Plexus and Peripheral Nerve Program, founded under the leadership of the late Dr. Lynda Yang, as a case study for how these principles can be applied to build and operationalize a successful interdisciplinary team. They suggest that these same techniques can be used to create interdisciplinary research groups in other areas of neurosurgery.


Asunto(s)
Plexo Braquial , Neurocirugia , Humanos , Investigación Interdisciplinaria , Grupo de Atención al Paciente , Procedimientos Neuroquirúrgicos , Plexo Braquial/cirugía
6.
Plast Reconstr Surg ; 151(1): 85e-98e, 2023 01 01.
Artículo en Inglés | MEDLINE | ID: mdl-36219869

RESUMEN

BACKGROUND: Acute flaccid myelitis (AFM) is a devastating neurologic condition in children, manifesting as acute limb weakness and/or paralysis. Despite increased awareness of AFM following initiation of U.S. surveillance in 2014, no treatment consensus exists. The purpose of this systematic review was to summarize the most current knowledge regarding AFM epidemiology, cause, clinical features, diagnosis, and supportive and operative management, including nerve transfer. METHODS: The authors systematically reviewed the literature based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines using multiple databases to search the keywords ("acute flaccid myelitis"), ('acute flaccid myelitis'/exp OR 'acute flaccid myelitis'), and (Acute AND flaccid AND myelitis). Included articles reported on (1) AFM diagnosis and (2) patient-specific data regarding epidemiology, cause, clinical features, diagnostic features, or management of AFM. RESULTS: Ninety-nine articles were included in this review. The precise cause and pathophysiologic mechanism of AFM remain undetermined, but AFM is strongly associated with nonpolio enterovirus infections. Clinical presentation typically comprises preceding viral prodrome, pleocytosis, spinal cord lesions on T2-weighted magnetic resonance imaging, and acute onset of flaccid weakness/paralysis with hyporeflexia in at least one extremity. Supportive care includes medical therapy and rehabilitation. Early studies of nerve transfer for AFM have shown favorable outcomes for patients with persistent weakness. CONCLUSIONS: Supportive care and physical therapy are the foundation of a multidisciplinary approach to managing AFM. For patients with persistent limb weakness, nerve transfer has shown promise for improving function in distal muscle groups. Surgeons must consider potential spontaneous recovery, patient selection, donor nerve availability, recipient nerve appropriateness, and procedure timing.


Asunto(s)
Mielitis , Transferencia de Nervios , Enfermedades Neuromusculares , Niño , Humanos , Transferencia de Nervios/efectos adversos , Enfermedades Neuromusculares/diagnóstico , Enfermedades Neuromusculares/terapia , Mielitis/diagnóstico , Mielitis/terapia , Parálisis/etiología , Hipotonía Muscular
7.
Neurosurgery ; 2023 Dec 18.
Artículo en Inglés | MEDLINE | ID: mdl-38108400

RESUMEN

BACKGROUND AND OBJECTIVES: Neonatal brachial plexus palsy (NBPP) almost universally affects movement at the shoulder, elbow, and forearm. Timing of nerve reconstruction surgery to optimize long-term outcomes remains unknown. This study aimed to determine if timing of nerve reconstruction affects long-term recovery of an active range of motion (AROM) at the shoulder, elbow, and forearm in NBPP. METHODS: We interrogated a prospectively collected database of all patients with NBPP who underwent primary nerve surgery at a single tertiary referral center between 2005 and 2020. The cohort was divided into those who underwent surgery at ≤6 or >6 months old and ≤9 or >9 months old. AROM for shoulder abduction, forward flexion, and external rotation, elbow flexion and extension, and forearm supination were collected at each visit. RESULTS: Ninety-nine children were included in the analysis; 28 underwent surgery at ≤6 months old, 71 at >6 months, 74 at ≤9 months, and 25 at >9 months. There was no difference in AROM at 5 years for any of the movements between the ≤6- and >6-month groups. The ≤9-month group had significantly better shoulder forward flexion and elbow extension AROM than the >9-month group at a 5-year follow-up and better forearm supination at up to a 15-year follow-up. Patients who presented earlier were more likely to have earlier operations. CONCLUSION: Surgery before 9 months may improve long-term upper extremity recovery in NBPP. Early referral should be encouraged to optimize timing of operative intervention.

8.
Oper Neurosurg (Hagerstown) ; 24(4): 460-467, 2023 04 01.
Artículo en Inglés | MEDLINE | ID: mdl-36701661

RESUMEN

BACKGROUND: Cushing disease represents a challenge for neurosurgeons, with high recurrence rates reported. Characteristics associated with remission are incompletely understood; thus, an intraoperative predictor for outcome would be valuable for assessing resection of adrenocorticotropic hormone (ACTH) secreting tissue. OBJECTIVE: To evaluate whether intraoperative ACTH measurement could predict outcome after surgery for Cushing disease. METHODS: Retrospective cohort study of 55 consecutive encounters with Cushing disease who had peripheral plasma ACTH levels measured intraoperatively before, during, and after tumor resection. The primary outcome measure was remission, defined by either 2 negative 24-hour urine free cortisol or 2 negative midnight salivary cortisol measurements. A logistic regression machine learning model was generated using recursive feature elimination. RESULTS: Fifty-five operative encounters, comprising 49 unique patients, had a mean follow-up of 2.73 years (±2.11 years) and a median follow-up of 2.07 years. Remission was achieved in 69.1% (n = 38) of all operations and in 78.0% (n = 32) of those without cavernous sinus invasion. The final ACTH level measured intraoperatively correctly predicted outcome (area under the curve = 0.766; P value = .002). The odds ratio of remission in patients with the lowest quartile vs highest quartile final intraoperative ACTH was 23.4 ( P value = .002). Logistic regression machine learning model resulted in incorporating postoperative day 1 morning cortisol, final intraoperative ACTH that predicted outcome with an average area under the curve of 0.80 ( P = .0027). CONCLUSION: Intraoperative ACTH may predict outcome after surgery in Cushing disease; furthermore, investigation is warranted.


Asunto(s)
Hipersecreción de la Hormona Adrenocorticotrópica Pituitaria (HACT) , Humanos , Hipersecreción de la Hormona Adrenocorticotrópica Pituitaria (HACT)/cirugía , Hipersecreción de la Hormona Adrenocorticotrópica Pituitaria (HACT)/patología , Estudios Retrospectivos , Hidrocortisona , Hormona Adrenocorticotrópica
9.
J Neurosurg Pediatr ; 29(6): 727-732, 2022 Jun 01.
Artículo en Inglés | MEDLINE | ID: mdl-35334468

RESUMEN

OBJECTIVE: Standard, physician-elicited clinical assessment tools for the evaluation of function after nerve reconstruction for neonatal brachial plexus palsy (NBPP) do not accurately reflect real-world arm function. Wearable activity monitors allow for the evaluation of patient-initiated, spontaneous arm movement during activities of daily living. In this pilot study, the authors demonstrate the feasibility of using body-worn sensor technology to quantify spontaneous arm movement in children with NBPP 10 years after nerve reconstruction and report the timing and magnitude of recovered arm movement. METHODS: Eight children with NBPP who underwent brachial plexus reconstruction approximately 10 years prior were recruited to take part in this single-institution prospective pilot study. Per the treatment protocol of the authors' institution, operated patients had severe, nonrecovering nerve function at the time of surgery. The patients were fitted with an activity monitoring device on each of the affected and unaffected arms, which were worn for 7 consecutive days. The duration (VT) and power (VM) with which each arm moved during the patient's normal daily activities were extracted from the accelerometry data and ratios comparing the affected and unaffected arms were calculated. Demographic data and standard physician-elicited clinical measures of upper-extremity function were also collected. RESULTS: Three children underwent nerve grafting and transfer and 5 children underwent graft repair only. The mean (± SD) active range of motion was 98° ± 53° for shoulder abduction, 130° ± 24° for elbow flexion, and 39° ± 34° for shoulder external rotation. The median Medical Research Council grade was at least 2.5 for all muscle groups. The median Mallet grade was at least 2 for all categories, and 13.5 total. The VT ratio was 0.82 ± 0.08 and the VM ratio was 0.53 ± 0.12. CONCLUSIONS: Wearable activity monitors such as accelerometers can be used to quantify spontaneous arm movement in children who underwent nerve reconstruction for NBPP at long-term follow-up. These data more accurately reflect complex, goal-oriented movement needed to perform activities of daily living. Notably, despite severe, nonrecovering nerve function early in life, postsurgical NBPP patients use their affected arms more than 80% of the time that they use their unaffected arms, paralleling results in patients with NBPP who recovered spontaneously. These data represent the first long-term, real-world evidence to support brachial plexus reconstruction for patients with NBPP.


Asunto(s)
Neuropatías del Plexo Braquial , Parálisis Neonatal del Plexo Braquial , Transferencia de Nervios , Dispositivos Electrónicos Vestibles , Recién Nacido , Niño , Humanos , Parálisis Neonatal del Plexo Braquial/cirugía , Neuropatías del Plexo Braquial/cirugía , Actividades Cotidianas , Proyectos Piloto , Estudios Prospectivos , Transferencia de Nervios/métodos , Extremidad Superior/cirugía , Rango del Movimiento Articular/fisiología , Resultado del Tratamiento
10.
Pediatr Clin North Am ; 68(4): 775-782, 2021 08.
Artículo en Inglés | MEDLINE | ID: mdl-34247708

RESUMEN

With increasing use of intracranial imaging, the diagnosis of benign intracranial cysts is becoming more frequent in the pediatric population. These lesions are usually incidentally discovered during the work-up of unrelated symptoms. Most do not require treatment and many do not even require imaging follow-up. When symptomatic, symptoms of these lesions are usually caused by local mass effect. Symptomatic lesions warrant neurosurgical evaluation, and may require surgical intervention in rare, well-selected cases. This article describes three common benign intracranial cysts found in the pediatric population: arachnoid cysts, choroid cysts, and pineal cysts.


Asunto(s)
Quistes Aracnoideos/diagnóstico por imagen , Hallazgos Incidentales , Monitoreo Fisiológico , Atención Primaria de Salud/organización & administración , Quistes Aracnoideos/patología , Niño , Diagnóstico Diferencial , Humanos , Imagen por Resonancia Magnética , Factores de Riesgo
11.
Clin Neurol Neurosurg ; 207: 106737, 2021 08.
Artículo en Inglés | MEDLINE | ID: mdl-34134009

RESUMEN

OBJECTIVE: The diagnosis of unruptured intracranial aneurysms (UIAs) is being made more frequently in elderly patients. The goal of this study is to evaluate complications and clinical outcome in patients ≥ 60 years-old who underwent clipping of UIAs. METHODS: We performed a retrospective cohort study. Clinical outcome (modified Rankin scale score) was determined at the latest clinical follow-up. Complications and outcomes were compared between age groups (60-69, 70-80) and subgroups (60-64, 65-69, 70-74, and >75). RESULTS: The study population consisted of 255 patients (range 60-80 years-old) who underwent 262 clipping procedures for UIAs. Mean follow-up duration was 15.6 months (± 27.5). Major complications occurred in 20 patients (7.6%) and mortality in 3 patients (1.1%). Medical complications occurred in 26 patients (10%). Mean length of hospital-stay was 4.7 days (± 5.8). 89.6% were discharged to home. 87.8% had a favorable clinical outcome. The 70-80 age group had significantly more complications (P = 0.03) than the 60-69 group and a significantly longer hospital stay (6.02 vs. 4.3 days, P = 0.04). The older group was less likely to discharge to home and more likely to require rehabilitation (P = 0.002). Favorable clinical outcome did not significantly differ between the two groups (85.7% vs. 88.4%, P = 0.56). There was a trend for increasing complications from the younger to older subgroups (P = 0.008) and a reduction in the likelihood to discharge to home (P < 0.0001). The rate of ultimate favorable clinical outcome did not differ significantly between subgroups (P = 0.79). CONCLUSION: Although complications, length of hospital-stay, and discharge to non-home destinations increase with older age, the majority of patients ≥ 60 may have favorable clinical outcomes.


Asunto(s)
Aneurisma Intracraneal/cirugía , Procedimientos Neuroquirúrgicos/efectos adversos , Procedimientos Neuroquirúrgicos/métodos , Resultado del Tratamiento , Anciano , Anciano de 80 o más Años , Estudios de Cohortes , Femenino , Humanos , Masculino , Persona de Mediana Edad , Complicaciones Posoperatorias/epidemiología , Complicaciones Posoperatorias/etiología , Estudios Retrospectivos , Instrumentos Quirúrgicos
12.
Oper Neurosurg (Hagerstown) ; 21(1): E38, 2021 06 15.
Artículo en Inglés | MEDLINE | ID: mdl-33825885

RESUMEN

Schwannomas are typically benign tumors that arise from the sheaths of nerves in the peripheral nervous system. In the spine, schwannomas usually arise from spinal nerve roots and are therefore extramedullary in nature. Surgical resection-achieving a gross total resection, is the main treatment modality and is typically curative for patients with sporadic tumors. In this video, we present the case of a 38-yr-old male with worsening left leg radiculopathy, found to have a lumbar schwannoma. Preoperative imaging demonstrated that the tumor was at the level of L4-L5. A laminectomy at this level was performed with gross total resection of the tumor. The key points of the video include use of intraoperative fluoroscopy to confirm surgical level and help plan surgical exposure, use of ultrasound for intradural tumor localization, and advocating for maximum safe resection using neurostimulation. The patient tolerated the surgery well without any complications. He was discharged home with no additional therapy needed. Appropriate patient consent was obtained.


Asunto(s)
Neurilemoma , Radiculopatía , Neoplasias de la Médula Espinal , Adulto , Humanos , Laminectomía , Masculino , Neurilemoma/diagnóstico por imagen , Neurilemoma/cirugía , Neoplasias de la Médula Espinal/diagnóstico por imagen , Neoplasias de la Médula Espinal/cirugía , Raíces Nerviosas Espinales/diagnóstico por imagen , Raíces Nerviosas Espinales/cirugía
13.
Neurosurgery ; 88(4): 838-845, 2021 03 15.
Artículo en Inglés | MEDLINE | ID: mdl-33483747

RESUMEN

BACKGROUND: Machine learning (ML)-based predictive models are increasingly common in neurosurgery, but typically require large databases of discrete variables for training. Natural language processing (NLP) can extract meaningful data from unstructured text. OBJECTIVE: To present an NLP model that predicts nonhome discharge and a point-of-care implementation. METHODS: We retrospectively collected age, preoperative notes, and radiology reports from 595 adults who underwent meningioma resection in an academic center from 1995 to 2015. A total of 32 algorithms were trained with the data; the 3 best performing algorithms were combined to form an ensemble. Predictive ability, assessed by area under the receiver operating characteristic curve (AUC) and calibration, was compared to a previously published model utilizing 52 neurosurgeon-selected variables. We then built a multi-institutional model by incorporating notes from 693 patients at another center into algorithm training. Permutation importance was used to analyze the relative importance of each input to model performance. Word clouds and non-negative matrix factorization were used to analyze predictive features of text. RESULTS: The single-institution NLP model predicted nonhome discharge with AUC of 0.80 (95% CI = 0.74-0.86) on internal and 0.76 on holdout validation compared to AUC of 0.77 (95% CI = 0.73-0.81) and 0.74 for the 52-variable ensemble. The multi-institutional model performed similarly well with AUC = 0.78 (95% CI = 0.74-0.81) on internal and 0.76 on holdout validation. Preoperative notes most influenced predictions. The model is available at http://nlp-home.insds.org. CONCLUSION: ML and NLP are underutilized in neurosurgery. Here, we construct a multi-institutional NLP model that predicts nonhome discharge.


Asunto(s)
Aprendizaje Automático/tendencias , Neoplasias Meníngeas/cirugía , Meningioma/cirugía , Procesamiento de Lenguaje Natural , Alta del Paciente/tendencias , Adulto , Anciano , Algoritmos , Bases de Datos Factuales/tendencias , Femenino , Humanos , Masculino , Neoplasias Meníngeas/diagnóstico , Meningioma/diagnóstico , Persona de Mediana Edad , Valor Predictivo de las Pruebas , Estudios Retrospectivos
14.
Neurosurgery ; 85(3): 384-393, 2019 09 01.
Artículo en Inglés | MEDLINE | ID: mdl-30113665

RESUMEN

BACKGROUND: Current outcomes prediction tools are largely based on and limited by regression methods. Utilization of machine learning (ML) methods that can handle multiple diverse inputs could strengthen predictive abilities and improve patient outcomes. Inpatient length of stay (LOS) is one such outcome that serves as a surrogate for patient disease severity and resource utilization. OBJECTIVE: To develop a novel method to systematically rank, select, and combine ML algorithms to build a model that predicts LOS following craniotomy for brain tumor. METHODS: A training dataset of 41 222 patients who underwent craniotomy for brain tumor was created from the National Inpatient Sample. Twenty-nine ML algorithms were trained on 26 preoperative variables to predict LOS. Trained algorithms were ranked by calculating the root mean square logarithmic error (RMSLE) and top performing algorithms combined to form an ensemble. The ensemble was externally validated using a dataset of 4592 patients from the National Surgical Quality Improvement Program. Additional analyses identified variables that most strongly influence the ensemble model predictions. RESULTS: The ensemble model predicted LOS with RMSLE of .555 (95% confidence interval, .553-.557) on internal validation and .631 on external validation. Nonelective surgery, preoperative pneumonia, sodium abnormality, or weight loss, and non-White race were the strongest predictors of increased LOS. CONCLUSION: An ML ensemble model predicts LOS with good performance on internal and external validation, and yields clinical insights that may potentially improve patient outcomes. This systematic ML method can be applied to a broad range of clinical problems to improve patient care.


Asunto(s)
Algoritmos , Neoplasias Encefálicas/cirugía , Reglas de Decisión Clínica , Tiempo de Internación , Aprendizaje Automático , Femenino , Humanos , Pacientes Internos , Masculino , Persona de Mediana Edad , Pronóstico , Análisis de Regresión
15.
J Neurosurg ; 131(2): 507-516, 2018 09 21.
Artículo en Inglés | MEDLINE | ID: mdl-30239321

RESUMEN

OBJECTIVE: Efficient allocation of resources in the healthcare system enables providers to care for more and needier patients. Identifying drivers of total charges for transsphenoidal surgery (TSS) for pituitary tumors, which are poorly understood, represents an opportunity for neurosurgeons to reduce waste and provide higher-quality care for their patients. In this study the authors used a large, national database to build machine learning (ML) ensembles that directly predict total charges in this patient population. They then interrogated the ensembles to identify variables that predict high charges. METHODS: The authors created a training data set of 15,487 patients who underwent TSS between 2002 and 2011 and were registered in the National Inpatient Sample. Thirty-two ML algorithms were trained to predict total charges from 71 collected variables, and the most predictive algorithms combined to form an ensemble model. The model was internally and externally validated to demonstrate generalizability. Permutation importance and partial dependence analyses were performed to identify the strongest drivers of total charges. Given the overwhelming influence of length of stay (LOS), a second ensemble excluding LOS as a predictor was built to identify additional drivers of total charges. RESULTS: An ensemble model comprising 3 gradient boosted tree classifiers best predicted total charges (root mean square logarithmic error = 0.446; 95% CI 0.439-0.453; holdout = 0.455). LOS was by far the strongest predictor of total charges, increasing total predicted charges by approximately $5000 per day.In the absence of LOS, the strongest predictors of total charges were admission type, hospital region, race, any postoperative complication, and hospital ownership type. CONCLUSIONS: ML ensembles predict total charges for TSS with good fidelity. The authors identified extended LOS, nonelective admission type, non-Southern hospital region, minority race, postoperative complication, and private investor hospital ownership as drivers of total charges and potential targets for cost-lowering interventions.


Asunto(s)
Adenoma/cirugía , Costos y Análisis de Costo/tendencias , Costos de la Atención en Salud/tendencias , Aprendizaje Automático/tendencias , Neoplasias Hipofisarias/cirugía , Seno Esfenoidal/cirugía , Adenoma/economía , Adenoma/epidemiología , Adulto , Anciano , Costos y Análisis de Costo/métodos , Bases de Datos Factuales/economía , Bases de Datos Factuales/tendencias , Femenino , Predicción , Humanos , Masculino , Persona de Mediana Edad , Neoplasias Hipofisarias/economía , Neoplasias Hipofisarias/epidemiología , Estados Unidos/epidemiología
17.
J Neurol Surg B Skull Base ; 79(2): 123-130, 2018 Apr.
Artículo en Inglés | MEDLINE | ID: mdl-29868316

RESUMEN

Objective Machine learning (ML) algorithms are powerful tools for predicting patient outcomes. This study pilots a novel approach to algorithm selection and model creation using prediction of discharge disposition following meningioma resection as a proof of concept. Materials and Methods A diversity of ML algorithms were trained on a single-institution database of meningioma patients to predict discharge disposition. Algorithms were ranked by predictive power and top performers were combined to create an ensemble model. The final ensemble was internally validated on never-before-seen data to demonstrate generalizability. The predictive power of the ensemble was compared with a logistic regression. Further analyses were performed to identify how important variables impact the ensemble. Results Our ensemble model predicted disposition significantly better than a logistic regression (area under the curve of 0.78 and 0.71, respectively, p = 0.01). Tumor size, presentation at the emergency department, body mass index, convexity location, and preoperative motor deficit most strongly influence the model, though the independent impact of individual variables is nuanced. Conclusion Using a novel ML technique, we built a guided ML ensemble model that predicts discharge destination following meningioma resection with greater predictive power than a logistic regression, and that provides greater clinical insight than a univariate analysis. These techniques can be extended to predict many other patient outcomes of interest.

19.
Surg Neurol Int ; 8: 220, 2017.
Artículo en Inglés | MEDLINE | ID: mdl-28966826

RESUMEN

BACKGROUND: Identifying risk factors for negative postoperative outcomes is an important part of providing quality care. Here, we build machine learning (ML) ensembles to model the independent impact of presurgical comorbidities on discharge disposition and length of stay (LOS) following brain tumor resection from the HCUP National Inpatient Sample (NIS). METHODS: We performed a retrospective cohort study of 41,222 patients who underwent craniotomy for brain tumors during 2002-2011 and were registered in the NIS. Twenty-six ML algorithms were trained on prehospitalization variables to predict nonhome discharge and extended LOS (>7 days), and the most predictive algorithms combined to create ensemble models. Models were validated to demonstrate generalizability. Analysis was done to identify which and how specific comorbidities influence ensemble predictions. RESULTS: Receiver operating curve analysis showed area under the curve of 0.796 and 0.824 for the disposition and LOS ensembles, respectively. The disposition ensemble was most strongly influenced by preoperative paralysis and fluid/electrolyte abnormalities, which independently increased the risk of nonhome discharge in craniotomy patients by 35.4% and 13.9%, respectively. The LOS ensemble was most strongly influenced by the presence of preoperative paralysis, fluid/electrolyte abnormalities, and other nonparalysis neurological deficits, which independently increased the risk of extended LOS in craniotomy patients by 20.4%, 22.5%, and 38.3%, respectively. CONCLUSIONS: In this study, we used ML ensembles to identify preoperative comorbidities that increased the risk of nonhome discharge and extended LOS following craniotomy for brain tumor. Recognizing these risk factors for poor postsurgical outcomes can improve patient counseling and offer opportunities for quality improvement.

20.
World Neurosurg ; 104: 24-38, 2017 Aug.
Artículo en Inglés | MEDLINE | ID: mdl-28478245

RESUMEN

BACKGROUND: Racial disparities exist in health care, frequently resulting in unfavorable outcomes for minority patients. Here, we use guided machine learning (ML) ensembles to model the impact of race on discharge disposition and length of stay (LOS) after brain tumor surgery from the Healthcare Cost and Utilization Project National Inpatient Sample. METHODS: We performed a retrospective cohort study of 41,222 patients who underwent craniotomies for brain tumors from 2002 to 2011 and were registered in the National Inpatient Sample. Twenty-six ML algorithms were trained on prehospitalization variables to predict non-home discharge and extended LOS (>7 days) after brain tumor resection, and the most predictive algorithms combined to create ensemble models. Partial dependence analysis was performed to measure the independent impact of race on the ensembles. RESULTS: The guided ML ensembles predicted non-home disposition (area under the curve, 0.796) and extended LOS (area under the curve, 0.824) with good discrimination. Partial dependence analysis showed that black race increases the risk of non-home discharge and extended LOS over white race by 6.9% and 6.5%, respectively. Other, nonblack race increases the risk of extended LOS over white race by 6.0%. The impact of race on these outcomes is not seen when analyzing the general inpatient or general operative population. CONCLUSIONS: Minority race independently increases the risk of extended LOS and black race increases the risk of non-home discharge in patients undergoing brain tumor resection, a finding not mimicked in the general inpatient or operative population. Recognition of the influence of race on discharge and LOS could generate interventions that may improve outcomes in this population.


Asunto(s)
Negro o Afroamericano/estadística & datos numéricos , Neoplasias Encefálicas/etnología , Neoplasias Encefálicas/cirugía , Craneotomía/mortalidad , Tiempo de Internación/estadística & datos numéricos , Alta del Paciente/estadística & datos numéricos , Grupos Raciales/estadística & datos numéricos , Neoplasias Encefálicas/mortalidad , Craneotomía/estadística & datos numéricos , Femenino , Humanos , Masculino , Persona de Mediana Edad , Prevalencia , Estudios Retrospectivos , Factores de Riesgo , Tasa de Supervivencia , Estados Unidos/etnología
SELECCIÓN DE REFERENCIAS
DETALLE DE LA BÚSQUEDA