RESUMEN
OBJECTIVES: Non-contrast computed tomography of the brain (NCCTB) is commonly used to detect intracranial pathology but is subject to interpretation errors. Machine learning can augment clinical decision-making and improve NCCTB scan interpretation. This retrospective detection accuracy study assessed the performance of radiologists assisted by a deep learning model and compared the standalone performance of the model with that of unassisted radiologists. METHODS: A deep learning model was trained on 212,484 NCCTB scans drawn from a private radiology group in Australia. Scans from inpatient, outpatient, and emergency settings were included. Scan inclusion criteria were age ≥ 18 years and series slice thickness ≤ 1.5 mm. Thirty-two radiologists reviewed 2848 scans with and without the assistance of the deep learning system and rated their confidence in the presence of each finding using a 7-point scale. Differences in AUC and Matthews correlation coefficient (MCC) were calculated using a ground-truth gold standard. RESULTS: The model demonstrated an average area under the receiver operating characteristic curve (AUC) of 0.93 across 144 NCCTB findings and significantly improved radiologist interpretation performance. Assisted and unassisted radiologists demonstrated an average AUC of 0.79 and 0.73 across 22 grouped parent findings and 0.72 and 0.68 across 189 child findings, respectively. When assisted by the model, radiologist AUC was significantly improved for 91 findings (158 findings were non-inferior), and reading time was significantly reduced. CONCLUSIONS: The assistance of a comprehensive deep learning model significantly improved radiologist detection accuracy across a wide range of clinical findings and demonstrated the potential to improve NCCTB interpretation. CLINICAL RELEVANCE STATEMENT: This study evaluated a comprehensive CT brain deep learning model, which performed strongly, improved the performance of radiologists, and reduced interpretation time. The model may reduce errors, improve efficiency, facilitate triage, and better enable the delivery of timely patient care. KEY POINTS: ⢠This study demonstrated that the use of a comprehensive deep learning system assisted radiologists in the detection of a wide range of abnormalities on non-contrast brain computed tomography scans. ⢠The deep learning model demonstrated an average area under the receiver operating characteristic curve of 0.93 across 144 findings and significantly improved radiologist interpretation performance. ⢠The assistance of the comprehensive deep learning model significantly reduced the time required for radiologists to interpret computed tomography scans of the brain.
Asunto(s)
Aprendizaje Profundo , Adolescente , Humanos , Radiografía , Radiólogos , Estudios Retrospectivos , Tomografía Computarizada por Rayos X/métodos , AdultoRESUMEN
Natural language processing (NLP), a domain of artificial intelligence (AI) that models human language, has been used in medicine to automate diagnostics, detect adverse events, support decision making and predict clinical outcomes. However, applications to the clinical neurosciences appear to be limited. NLP has matured with the implementation of deep transformer models (e.g., XLNet, BERT, T5, and RoBERTa) and transfer learning. The objectives of this study were to (1) systematically review NLP applications in the clinical neurosciences, and (2) explore NLP analysis to facilitate literature synthesis, providing clear examples to demonstrate the potential capabilities of these technologies for a clinical audience. Our NLP analysis consisted of keyword identification, text summarization and document classification. A total of 48 articles met inclusion criteria. NLP has been applied in the clinical neurosciences to facilitate literature synthesis, data extraction, patient identification, automated clinical reporting and outcome prediction. The number of publications applying NLP has increased rapidly over the past five years. Document classifiers trained to differentiate included and excluded articles demonstrated moderate performance (XLNet AUC = 0.66, BERT AUC = 0.59, RoBERTa AUC = 0.62). The T5 transformer model generated acceptable abstract summaries. The application of NLP has the potential to enhance research and practice in the clinical neurosciences.
Asunto(s)
Procesamiento de Lenguaje Natural , Neurociencias , Inteligencia Artificial , Humanos , Aprendizaje AutomáticoRESUMEN
BACKGROUND: Robotic (RTKA) and computer-navigated total knee arthroplasty (CNTKA) are increasingly replacing manual techniques in orthopaedic surgery. This systematic review compared clinical outcomes associated with RTKA and CNTKA and investigated the utility of natural language processing (NLP) for the literature synthesis. METHODS: A comprehensive search strategy was implemented. Results of included studies were combined and analysed. A transfer learning approach was applied to train deep NLP classifiers (BERT, RoBERTa and XLNet), with cross-validation, to partially automate the systematic review process. RESULTS: 52 studies were included, comprising 5,067 RTKA and 2,108 CNTKA. Complication rates were 0-22% and 0-16% and surgical time was 70-116 and 77-102 min for RTKA and CNTKA, respectively. Technical failures were more commonly associated with RTKA (8%) than CNTKA (2-4%). Patient satisfaction was equivalent (94%). RTKA was associated with a higher likelihood of achieving target alignment, less femoral notching, shorter operative time and shorter length of stay. NLP models demonstrated moderate performance (AUC = 0.65-0.68). CONCLUSIONS: RTKA and CNTKA appear to be associated with similarly positive clinical outcomes. Further work is required to determine whether the two techniques differ significantly with regard to specific outcome measures. NLP shows promise for facilitating the systematic review process.
Asunto(s)
Artroplastia de Reemplazo de Rodilla , Procedimientos Quirúrgicos Robotizados , Artroplastia de Reemplazo de Rodilla/efectos adversos , Artroplastia de Reemplazo de Rodilla/métodos , Computadores , Humanos , Aprendizaje Automático , Tempo Operativo , Procedimientos Quirúrgicos Robotizados/efectos adversos , Procedimientos Quirúrgicos Robotizados/métodosRESUMEN
Machine learning (ML) involves algorithms learning patterns in large, complex datasets to predict and classify. Algorithms include neural networks (NN), logistic regression (LR), and support vector machines (SVM). ML may generate substantial improvements in neurosurgery. This systematic review assessed the current state of neurosurgical ML applications and the performance of algorithms applied. Our systematic search strategy yielded 6866 results, 70 of which met inclusion criteria. Performance statistics analyzed included area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, and specificity. Natural language processing (NLP) was used to model topics across the corpus and to identify keywords within surgical subspecialties. ML applications were heterogeneous. The densest cluster of studies focused on preoperative evaluation, planning, and outcome prediction in spine surgery. The main algorithms applied were NN, LR, and SVM. Input and output features varied widely and were listed to facilitate future research. The accuracy (F(2,19) = 6.56, p < 0.01) and specificity (F(2,16) = 5.57, p < 0.01) of NN, LR, and SVM differed significantly. NN algorithms demonstrated significantly higher accuracy than LR. SVM demonstrated significantly higher specificity than LR. We found no significant difference between NN, LR, and SVM AUC and sensitivity. NLP topic modeling reached maximum coherence at seven topics, which were defined by modeling approach, surgery type, and pathology themes. Keywords captured research foci within surgical domains. ML technology accurately predicts outcomes and facilitates clinical decision-making in neurosurgery. NNs frequently outperformed other algorithms on supervised learning tasks. This study identified gaps in the literature and opportunities for future neurosurgical ML research.
Asunto(s)
Inteligencia Artificial , Sistemas de Apoyo a Decisiones Clínicas , Aprendizaje Automático , Neurocirugia/métodos , Aprendizaje Profundo , Humanos , Procedimientos Neuroquirúrgicos/métodos , Máquina de Vectores de SoporteRESUMEN
OBJECTIVE Pedicle subtraction osteotomy (PSO) provides extensive correction in patients with fixed sagittal plane imbalance but is associated with high estimated blood loss (EBL). Anterior column realignment (ACR) with lateral graft placement and sectioning of the anterior longitudinal ligament allows restoration of lumbar lordosis (LL). The authors compare peri- and postoperative measures in 2 groups of patients undergoing correction of a sagittal plane imbalance, either through PSO or the use of lateral lumbar fusion and ACR with hyperlordotic (20°-30°) interbody cages, with stabilization through standard posterior instrumentation in all cases. METHODS The authors performed a retrospective chart review of cases involving a lumbar PSO or lateral lumbar interbody fusion and ACR (LLIF-ACR) between 2010 and 2015 at the authors' institution. Patients who had a PSO in the setting of a preexisting fusion that spanned more than 4 levels were excluded. Demographic characteristics, spinopelvic parameters, EBL, operative time, and LOS were analyzed and compared between patients treated with PSO and those treated with LLIF-ACR. RESULTS The PSO group included 14 patients and the LLIF-ACR group included 13 patients. The mean follow-up was 13 months in the LLIF-ACR group and 26 months in the PSO group. The mean EBL was significantly lower in the LLIF-ACR group, measuring approximately 50% of the mean EBL in the PSO group (1466 vs 2910 ml, p < 0.01). Total LL correction was equivalent between the 2 groups (35° in the PSO group, 31° in the LLIF-ACR group, p > 0.05), as was the preoperative PI-LL mismatch (33° in each group, p > 0.05) and the postoperative PI-LL mismatch (< 1° in each group, p = 0.05). The fusion rate as assessed by the need for reoperation due to pseudarthrosis was lower in the LLIF-ACR group but not significantly so (3 revisions in the PSO group due to pseudarthrosis vs 0 in the LLIF-ACR group, p > 0.5). The total operative time and LOS were not significantly different in the 2 groups. CONCLUSIONS This is the first direct comparison of the LLIF-ACR technique with the PSO in adult spinal deformity correction. The study demonstrates that the LLIF-ACR provides equivalent deformity correction with significantly reduced blood loss in patients with a previously unfused spine compared with the PSO. This technique provides a powerful means to avoid PSO in selected patients who require spinal deformity correction.
Asunto(s)
Pérdida de Sangre Quirúrgica/prevención & control , Lordosis/cirugía , Vértebras Lumbares/cirugía , Osteotomía/métodos , Huesos Pélvicos/cirugía , Fusión Vertebral/métodos , Anciano , Femenino , Estudios de Seguimiento , Humanos , Disco Intervertebral/diagnóstico por imagen , Disco Intervertebral/cirugía , Lordosis/diagnóstico por imagen , Vértebras Lumbares/anomalías , Vértebras Lumbares/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Osteotomía/efectos adversos , Huesos Pélvicos/anomalías , Huesos Pélvicos/diagnóstico por imagen , Diseño de Prótesis , Estudios Retrospectivos , Fusión Vertebral/instrumentaciónRESUMEN
Ischemic stroke is a leading cause of disability and death. Current treatments are limited. Stem cell therapy has been highlighted as a potentially effective treatment to mitigate damage and restore function, but efficacy results are mixed. This study aimed to systematically review the literature on stem cell therapies for early acute ischemic stroke; and identify opportunities for future research to facilitate the development of an effective stem cell-based treatment. Original research published within the last 10 years that focused on the evaluation of a stem cell-based treatment for acute ischemic stroke in adult patients or subjects was included. Risk of bias was assessed using the SYRCLE and Cochrane risk of bias tools for animal and human studies, respectively. 3,396 articles were screened, 58 full-text articles were reviewed and 33 met inclusion criteria. Many studies appeared to be at risk of bias. Study designs and results were heterogeneous. Most studies were preclinical and involved stem cell administration within 24 hours. Seven studies tested the effects of multiple administration timepoints and one investigated repeat dosing. Six studies were conducted in humans and stem cell administration ranged from 24 hours to 90 days post stroke. Most studies employed the use of mesenchymal stem cells. The most appropriate cell delivery method appeared to be intra-arterial. Evidence suggests that stem cell therapy may be associated with beneficial effects. A literature gap analysis identified numerous opportunities for treatment development.
Asunto(s)
Accidente Cerebrovascular Isquémico , Células-Madre Neurales , Trasplante de Células Madre , Humanos , Accidente Cerebrovascular Isquémico/terapia , Animales , Células-Madre Neurales/trasplante , Trasplante de Células Madre/métodosRESUMEN
OBJECTIVES: The aim of the study was to train and test supervised machine-learning classifiers to predict acoustic hearing preservation after CI using preoperative clinical data. STUDY DESIGN: Retrospective predictive modeling study of prospectively collected single-institution CI dataset. METHODS: One hundred and seventy-five patients from a REDCap database including 761 patients >18 years who underwent CI and had audiometric testing preoperatively and one month after surgery were included. The primary outcome variable was the lowest quartile change in acoustic hearing at one month after CI using various formulae (standard pure tone average, SPTA; low-frequency PTA, LFPTA). Analysis involved applying multivariate logistic regression to detect statistical associations and training and testing supervised learning classifiers. Classifier performance was assessed with numerous metrics including area under the receiver operating characteristic curve (AUC) and Matthews correlation coefficient (MCC). RESULTS: Lowest quartile change (indicating hearing preservation) in SPTA was positively associated with a history of meningitis, preoperative LFPTA, and preoperative SPTA. Lowest quartile change in SPTA was negatively associated with sudden hearing loss, noise exposure, aural fullness, and abnormal anatomy. Lowest quartile change in LFPTA was positively associated with preoperative LFPTA. Lowest quartile change in LFPTA was negatively associated with tobacco use. Random forest demonstrated the highest mean classification performance on the validation dataset when predicting each of the outcome variables. CONCLUSIONS: Machine learning demonstrated utility for predicting preservation of residual acoustic hearing in patients undergoing CI surgery, and the detected associations facilitated the interpretation of our machine-learning models. The models and statistical associations together may be used to facilitate improvements in shared clinical decision-making and patient outcomes. LEVEL OF EVIDENCE: 3 Laryngoscope, 134:926-936, 2024.
Asunto(s)
Implantación Coclear , Implantes Cocleares , Humanos , Estudios Retrospectivos , Resultado del Tratamiento , Audición , Aprendizaje Automático , Acústica , Audiometría de Tonos PurosRESUMEN
Limitations of the chest X-ray (CXR) have resulted in attempts to create machine learning systems to assist clinicians and improve interpretation accuracy. An understanding of the capabilities and limitations of modern machine learning systems is necessary for clinicians as these tools begin to permeate practice. This systematic review aimed to provide an overview of machine learning applications designed to facilitate CXR interpretation. A systematic search strategy was executed to identify research into machine learning algorithms capable of detecting >2 radiographic findings on CXRs published between January 2020 and September 2022. Model details and study characteristics, including risk of bias and quality, were summarized. Initially, 2248 articles were retrieved, with 46 included in the final review. Published models demonstrated strong standalone performance and were typically as accurate, or more accurate, than radiologists or non-radiologist clinicians. Multiple studies demonstrated an improvement in the clinical finding classification performance of clinicians when models acted as a diagnostic assistance device. Device performance was compared with that of clinicians in 30% of studies, while effects on clinical perception and diagnosis were evaluated in 19%. Only one study was prospectively run. On average, 128,662 images were used to train and validate models. Most classified less than eight clinical findings, while the three most comprehensive models classified 54, 72, and 124 findings. This review suggests that machine learning devices designed to facilitate CXR interpretation perform strongly, improve the detection performance of clinicians, and improve the efficiency of radiology workflow. Several limitations were identified, and clinician involvement and expertise will be key to driving the safe implementation of quality CXR machine learning systems.
RESUMEN
This retrospective case-control study evaluated the diagnostic performance of a commercially available chest radiography deep convolutional neural network (DCNN) in identifying the presence and position of central venous catheters, enteric tubes, and endotracheal tubes, in addition to a subgroup analysis of different types of lines/tubes. A held-out test dataset of 2568 studies was sourced from community radiology clinics and hospitals in Australia and the USA, and was then ground-truth labelled for the presence, position, and type of line or tube from the consensus of a thoracic specialist radiologist and an intensive care clinician. DCNN model performance for identifying and assessing the positioning of central venous catheters, enteric tubes, and endotracheal tubes over the entire dataset, as well as within each subgroup, was evaluated. The area under the receiver operating characteristic curve (AUC) was assessed. The DCNN algorithm displayed high performance in detecting the presence of lines and tubes in the test dataset with AUCs > 0.99, and good position classification performance over a subpopulation of ground truth positive cases with AUCs of 0.86-0.91. The subgroup analysis showed that model performance was robust across the various subtypes of lines or tubes, although position classification performance of peripherally inserted central catheters was relatively lower. Our findings indicated that the DCNN algorithm performed well in the detection and position classification of lines and tubes, supporting its use as an assistant for clinicians. Further work is required to evaluate performance in rarer scenarios, as well as in less common subgroups.
RESUMEN
BACKGROUND: Patients with pituitary lesions experience decrements in quality of life (QoL) and treatment aims to arrest or improve QoL decline. OBJECTIVE: To detect associations with QoL in trans-nasal endoscopic skull base surgery patients and train supervised learning classifiers to predict QoL improvement at 12 months. METHODS: A supervised learning analysis of a prospective multi-institutional dataset (451 patients) was conducted. QoL was measured using the anterior skull base surgery questionnaire (ASBS). Factors associated with QoL at baseline and at 12-month follow-up were identified using multivariate logistic regression. Multiple supervised learning models were trained to predict postoperative QoL improvement with five-fold cross-validation. RESULTS: ASBS at 12-month follow-up was significantly higher (132.19,SD = 24.87) than preoperative ASBS (121.87,SD = 25.72,p<0.05). High preoperative scores were significantly associated with institution, diabetes and lesions at the planum sphenoidale / tuberculum sella site. Patients with diabetes were five times less likely to report high preoperative QoL. Low preoperative QoL was significantly associated with female gender, a vision-related presentation, diabetes, secreting adenoma and the cavernous sinus site. Top quartile change in postoperative QoL at 12-month follow-up was negatively associated with baseline hypercholesterolemia, acromegaly and intraoperative CSF leak. Positive associations were detected for lesions at the sphenoid sinus site and deficient preoperative endocrine function. AdaBoost, logistic regression and neural network classifiers yielded the strongest predictive performance. CONCLUSION: It was possible to predict postoperative positive change in QoL at 12-month follow-up using perioperative data. Further development and implementation of these models may facilitate improvements in informed consent, treatment decision-making and patient QoL.
Asunto(s)
Neoplasias Hipofisarias , Calidad de Vida , Endoscopía , Femenino , Estudios de Seguimiento , Humanos , Neoplasias Hipofisarias/cirugía , Estudios Prospectivos , Base del Cráneo/cirugía , Resultado del TratamientoRESUMEN
Brain computed tomography (CTB) scans are widely used to evaluate intracranial pathology. The implementation and adoption of CTB has led to clinical improvements. However, interpretation errors occur and may have substantial morbidity and mortality implications for patients. Deep learning has shown promise for facilitating improved diagnostic accuracy and triage. This research charts the potential of deep learning applied to the analysis of CTB scans. It draws on the experience of practicing clinicians and technologists involved in development and implementation of deep learning-based clinical decision support systems. We consider the past, present and future of the CTB, along with limitations of existing systems as well as untapped beneficial use cases. Implementing deep learning CTB interpretation systems and effectively navigating development and implementation risks can deliver many benefits to clinicians and patients, ultimately improving efficiency and safety in healthcare.
Asunto(s)
Sistemas de Apoyo a Decisiones Clínicas , Aprendizaje Profundo , Humanos , Neuroimagen , Tomografía Computarizada por Rayos X/métodosRESUMEN
BACKGROUND: Motor vehicle accidents (MVA) represent a significant burden on health systems globally. Tens of thousands of people are injured in Australia every year and may experience significant disability. Associated economic costs are substantial. There is little literature on the health service utilization patterns of MVA patients. To fill this gap, this study has been designed to investigate temporal patterns of psychology and physiotherapy service utilization following transport-related injuries. METHOD: De-identified compensation data was provided by the Australian Transport Accident Commission. Utilization of physiotherapy and psychology services was analysed. The datasets contained 788 psychology and 3115 physiotherapy claimants and 22,522 and 118,453 episodes of service utilization, respectively. 582 claimants used both services, and their data were preprocessed to generate multidimensional time series. Time series clustering was applied using a mixture of hidden Markov models to identify the main distinct patterns of service utilization. Combinations of hidden states and clusters were evaluated and optimized using the Bayesian information criterion and interpretability. Cluster membership was further investigated using static covariates and multinomial logistic regression, and classified using high-performing classifiers (extreme gradient boosting machine, random forest and support vector machine) with 5-fold cross-validation. RESULTS: Four clusters of claimants were obtained from the clustering of the time series of service utilization. Service volumes and costs increased progressively from clusters 1 to 4. Membership of cluster 1 was positively associated with nerve damage and negatively associated with severe ABI and spinal injuries. Cluster 3 was positively associated with severe ABI, brain/head injury and psychiatric injury. Cluster 4 was positively associated with internal injuries. The classifiers were capable of classifying cluster membership with moderate to strong performance (AUC: 0.62-0.96). CONCLUSION: The available time series of post-accident psychology and physiotherapy service utilization were coalesced into four clusters that were clearly distinct in terms of patterns of utilization. In addition, pre-treatment covariates allowed prediction of a claimant's post-accident service utilization with reasonable accuracy. Such results can be useful for a range of decision-making processes, including the design of interventions aimed at improving claimant care and recovery.
Asunto(s)
Accidentes de Tránsito , Servicios de Salud , Australia , Teorema de Bayes , Humanos , Modalidades de FisioterapiaRESUMEN
Glioma is the most common primary intraparenchymal tumor of the brain and the 5-year survival rate of high-grade glioma is poor. Magnetic resonance imaging (MRI) is essential for detecting, characterizing and monitoring brain tumors but definitive diagnosis still relies on surgical pathology. Machine learning has been applied to the analysis of MRI data in glioma research and has the potential to change clinical practice and improve patient outcomes. This systematic review synthesizes and analyzes the current state of machine learning applications to glioma MRI data and explores the use of machine learning for systematic review automation. Various datapoints were extracted from the 153 studies that met inclusion criteria and analyzed. Natural language processing (NLP) analysis involved keyword extraction, topic modeling and document classification. Machine learning has been applied to tumor grading and diagnosis, tumor segmentation, non-invasive genomic biomarker identification, detection of progression and patient survival prediction. Model performance was generally strong (AUC = 0.87 ± 0.09; sensitivity = 0.87 ± 0.10; specificity = 0.0.86 ± 0.10; precision = 0.88 ± 0.11). Convolutional neural network, support vector machine and random forest algorithms were top performers. Deep learning document classifiers yielded acceptable performance (mean 5-fold cross-validation AUC = 0.71). Machine learning tools and data resources were synthesized and summarized to facilitate future research. Machine learning has been widely applied to the processing of MRI data in glioma research and has demonstrated substantial utility. NLP and transfer learning resources enabled the successful development of a replicable method for automating the systematic review article screening process, which has potential for shortening the time from discovery to clinical application in medicine.
Asunto(s)
Inteligencia Artificial/tendencias , Neoplasias Encefálicas/diagnóstico por imagen , Glioma/diagnóstico por imagen , Aprendizaje Automático/tendencias , Redes Neurales de la Computación , Neuroimagen/tendencias , Algoritmos , Neoplasias Encefálicas/cirugía , Glioma/cirugía , Humanos , Imagen por Resonancia Magnética/métodos , Imagen por Resonancia Magnética/tendencias , Neuroimagen/métodos , Procedimientos Neuroquirúrgicos/métodos , Procedimientos Neuroquirúrgicos/tendencias , Máquina de Vectores de SoporteRESUMEN
Despite its simple acquisition technique, the chest X-ray remains the most common first-line imaging tool for chest assessment globally. Recent evidence for image analysis using modern machine learning points to possible improvements in both the efficiency and the accuracy of chest X-ray interpretation. While promising, these machine learning algorithms have not provided comprehensive assessment of findings in an image and do not account for clinical history or other relevant clinical information. However, the rapid evolution in technology and evidence base for its use suggests that the next generation of comprehensive, well-tested machine learning algorithms will be a revolution akin to early advances in X-ray technology. Current use cases, strengths, limitations and applications of chest X-ray machine learning systems are discussed.
Asunto(s)
Aprendizaje Automático , Humanos , Procesamiento de Imagen Asistido por Computador , Radiografía , TóraxRESUMEN
OBJECTIVES: Artificial intelligence (AI) algorithms have been developed to detect imaging features on chest X-ray (CXR) with a comprehensive AI model capable of detecting 124 CXR findings being recently developed. The aim of this study was to evaluate the real-world usefulness of the model as a diagnostic assistance device for radiologists. DESIGN: This prospective real-world multicentre study involved a group of radiologists using the model in their daily reporting workflow to report consecutive CXRs and recording their feedback on level of agreement with the model findings and whether this significantly affected their reporting. SETTING: The study took place at radiology clinics and hospitals within a large radiology network in Australia between November and December 2020. PARTICIPANTS: Eleven consultant diagnostic radiologists of varying levels of experience participated in this study. PRIMARY AND SECONDARY OUTCOME MEASURES: Proportion of CXR cases where use of the AI model led to significant material changes to the radiologist report, to patient management, or to imaging recommendations. Additionally, level of agreement between radiologists and the model findings, and radiologist attitudes towards the model were assessed. RESULTS: Of 2972 cases reviewed with the model, 92 cases (3.1%) had significant report changes, 43 cases (1.4%) had changed patient management and 29 cases (1.0%) had further imaging recommendations. In terms of agreement with the model, 2569 cases showed complete agreement (86.5%). 390 (13%) cases had one or more findings rejected by the radiologist. There were 16 findings across 13 cases (0.5%) deemed to be missed by the model. Nine out of 10 radiologists felt their accuracy was improved with the model and were more positive towards AI poststudy. CONCLUSIONS: Use of an AI model in a real-world reporting environment significantly improved radiologist reporting and showed good agreement with radiologists, highlighting the potential for AI diagnostic support to improve clinical practice.
Asunto(s)
Inteligencia Artificial , Aprendizaje Profundo , Algoritmos , Humanos , Estudios Prospectivos , RadiólogosRESUMEN
OBJECTIVES: To evaluate the ability of a commercially available comprehensive chest radiography deep convolutional neural network (DCNN) to detect simple and tension pneumothorax, as stratified by the following subgroups: the presence of an intercostal drain; rib, clavicular, scapular or humeral fractures or rib resections; subcutaneous emphysema and erect versus non-erect positioning. The hypothesis was that performance would not differ significantly in each of these subgroups when compared with the overall test dataset. DESIGN: A retrospective case-control study was undertaken. SETTING: Community radiology clinics and hospitals in Australia and the USA. PARTICIPANTS: A test dataset of 2557 chest radiography studies was ground-truthed by three subspecialty thoracic radiologists for the presence of simple or tension pneumothorax as well as each subgroup other than positioning. Radiograph positioning was derived from radiographer annotations on the images. OUTCOME MEASURES: DCNN performance for detecting simple and tension pneumothorax was evaluated over the entire test set, as well as within each subgroup, using the area under the receiver operating characteristic curve (AUC). A difference in AUC of more than 0.05 was considered clinically significant. RESULTS: When compared with the overall test set, performance of the DCNN for detecting simple and tension pneumothorax was statistically non-inferior in all subgroups. The DCNN had an AUC of 0.981 (0.976-0.986) for detecting simple pneumothorax and 0.997 (0.995-0.999) for detecting tension pneumothorax. CONCLUSIONS: Hidden stratification has significant implications for potential failures of deep learning when applied in clinical practice. This study demonstrated that a comprehensively trained DCNN can be resilient to hidden stratification in several clinically meaningful subgroups in detecting pneumothorax.
Asunto(s)
Aprendizaje Profundo , Neumotórax , Algoritmos , Estudios de Casos y Controles , Humanos , Neumotórax/diagnóstico por imagen , Radiografía , Radiografía Torácica/métodos , Estudios RetrospectivosRESUMEN
BACKGROUND: Chest x-rays are widely used in clinical practice; however, interpretation can be hindered by human error and a lack of experienced thoracic radiologists. Deep learning has the potential to improve the accuracy of chest x-ray interpretation. We therefore aimed to assess the accuracy of radiologists with and without the assistance of a deep-learning model. METHODS: In this retrospective study, a deep-learning model was trained on 821 681 images (284 649 patients) from five data sets from Australia, Europe, and the USA. 2568 enriched chest x-ray cases from adult patients (≥16 years) who had at least one frontal chest x-ray were included in the test dataset; cases were representative of inpatient, outpatient, and emergency settings. 20 radiologists reviewed cases with and without the assistance of the deep-learning model with a 3-month washout period. We assessed the change in accuracy of chest x-ray interpretation across 127 clinical findings when the deep-learning model was used as a decision support by calculating area under the receiver operating characteristic curve (AUC) for each radiologist with and without the deep-learning model. We also compared AUCs for the model alone with those of unassisted radiologists. If the lower bound of the adjusted 95% CI of the difference in AUC between the model and the unassisted radiologists was more than -0·05, the model was considered to be non-inferior for that finding. If the lower bound exceeded 0, the model was considered to be superior. FINDINGS: Unassisted radiologists had a macroaveraged AUC of 0·713 (95% CI 0·645-0·785) across the 127 clinical findings, compared with 0·808 (0·763-0·839) when assisted by the model. The deep-learning model statistically significantly improved the classification accuracy of radiologists for 102 (80%) of 127 clinical findings, was statistically non-inferior for 19 (15%) findings, and no findings showed a decrease in accuracy when radiologists used the deep-learning model. Unassisted radiologists had a macroaveraged mean AUC of 0·713 (0·645-0·785) across all findings, compared with 0·957 (0·954-0·959) for the model alone. Model classification alone was significantly more accurate than unassisted radiologists for 117 (94%) of 124 clinical findings predicted by the model and was non-inferior to unassisted radiologists for all other clinical findings. INTERPRETATION: This study shows the potential of a comprehensive deep-learning model to improve chest x-ray interpretation across a large breadth of clinical practice. FUNDING: Annalise.ai.
Asunto(s)
Aprendizaje Profundo , Tamizaje Masivo/métodos , Modelos Biológicos , Interpretación de Imagen Radiográfica Asistida por Computador , Radiografía Torácica , Rayos X , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , Área Bajo la Curva , Inteligencia Artificial , Femenino , Humanos , Infecciones/diagnóstico , Infecciones/diagnóstico por imagen , Masculino , Persona de Mediana Edad , Curva ROC , Radiólogos , Estudios Retrospectivos , Traumatismos Torácicos/diagnóstico , Traumatismos Torácicos/diagnóstico por imagen , Neoplasias Torácicas/diagnóstico , Neoplasias Torácicas/diagnóstico por imagen , Adulto JovenRESUMEN
BACKGROUND: Deep brain stimulation (DBS) surgery is an option for patients experiencing medically resistant neurologic symptoms. DBS complications are rare; finding significant predictors requires a large number of surgeries. Machine learning algorithms may be used to effectively predict these outcomes. The aims of this study were to 1) investigate preoperative clinical risk factors and 2) build machine learning models to predict adverse outcomes. METHODS: This multicenter registry collected clinical and demographic characteristics of patients undergoing DBS surgery (n = 501) and tabulated occurrence of complications. Logistic regression was used to evaluate risk factors. Supervised learning algorithms were trained and validated on 70% and 30%, respectively, of both oversampled and original registry data. Performance was evaluated using area under the receiver operating characteristics curve (AUC), sensitivity, specificity, and accuracy. RESULTS: Logistic regression showed that the risk of complication was related to the operating institution in which the surgery was performed (odds ratio [OR] = 0.44, confidence interval [CI] = 0.25-0.78), body mass index (OR = 0.94, CI = 0.89-0.99), and diabetes (OR = 2.33, CI = 1.18-4.60). Patients with diabetes were almost 3× more likely to return to the operating room (OR = 2.78, CI = 1.31-5.88). Patients with a history of smoking were 4× more likely to experience postoperative infection (OR = 4.20, CI = 1.21-14.61). Supervised learning algorithms demonstrated high discrimination performance when predicting any complication (AUC = 0.86), a complication within 12 months (AUC = 0.91), return to the operating room (AUC = 0.88), and infection (AUC = 0.97). Age, body mass index, procedure side, gender, and a diagnosis of Parkinson disease were influential features. CONCLUSIONS: Multiple significant complication risk factors were identified, and supervised learning algorithms effectively predicted adverse outcomes in DBS surgery.
Asunto(s)
Algoritmos , Estimulación Encefálica Profunda/efectos adversos , Aprendizaje Automático , Complicaciones Posoperatorias/diagnóstico , Complicaciones Posoperatorias/etiología , Anciano , Estimulación Encefálica Profunda/tendencias , Femenino , Humanos , Masculino , Persona de Mediana Edad , Valor Predictivo de las Pruebas , Sistema de Registros , Estudios Retrospectivos , Factores de RiesgoRESUMEN
Surgical management of complex adult spinal deformities is of high risk, with a substantial risk of operative mortality. Current evidence shows that potential risk and morbidity resulting from surgery for complex spinal deformity may be minimized through risk-factor optimization. The multidisciplinary team care model includes neurosurgeons, orthopaedic surgeons, physiatrists, anesthesiologists, hospitalists, psychologists, physical therapists, specialized physician assistants, and nurses. The multidisciplinary care model mimics previously described integrated care pathways designed to offer a structured means of providing a comprehensive preoperative medical evaluation and evidence-based multimodal perioperative care. The role of each team member is illustrated in the case of a 66-year-old male patient with previous incomplete spinal cord injury, now presenting with Charcot spinal arthropathy and progressive vertebral-body destruction resulting in lumbar kyphosis.
Asunto(s)
Dolor de Espalda/cirugía , Grupo de Atención al Paciente , Vertebroplastia , Anciano , Humanos , MasculinoRESUMEN
Clinical decision making is susceptible to biases and can be improved with the application of predictive models and decision support systems (DSS). The purpose of this study was to develop a predictive risk stratification model and DSS that could accurately predict whether a patient was likely to be of high- or low-acuity discharge disposition (DD) status subsequent to DBS surgery. Data were collected for 135 DBS patients by reviewing medical records. Multivariate logistic regression was applied to develop the predictive algorithm. The two significant predictive models showed good fit and were calibrated by using AUROC curve analysis. The model predicting DD in all patients (nâ¯=â¯135) yielded a predictive accuracy of 91.9% (AUROCâ¯=â¯0.825, pâ¯<â¯.001). The model predicting DD in Parkinson's Disease patients (nâ¯=â¯91) yielded a predictive accuracy of 89.0% (AUROCâ¯=â¯0.853, pâ¯<â¯.001). Age was a significant predictor of DD across all patients (ORâ¯=â¯1.11, pâ¯<â¯.05) and BMI was a significant predictor of DD amongst Parkinson's Disease patients (ORâ¯=â¯1.16, pâ¯<â¯.05). It is possible to accurately predict the DD of DBS patients using routinely collected preoperative variables. The predictive algorithms were applied in the form of a model-driven DSS to assist in improving clinical decision making and patient safety.