RESUMEN
Cerebral microvascular occlusion is a common phenomenon throughout life that might require greater recognition as a mechanism of brain pathology. Failure to recanalize microvessels promptly may lead to the disruption of brain circuits and significant functional deficits. Haemodynamic forces and the fibrinolytic system are considered to be the principal mechanisms responsible for recanalization of occluded cerebral capillaries and terminal arterioles. Here we identify a previously unrecognized cellular mechanism that may also be critical for this recanalization. By using high-resolution fixed-tissue microscopy and two-photon imaging in living mice we observed that a large fraction of microemboli infused through the internal carotid artery failed to be lysed or washed out within 48 h. Instead, emboli were found to translocate outside the vessel lumen within 2-7 days, leading to complete re-establishment of blood flow and sparing of the vessel. Recanalization occurred by a previously unknown mechanism of microvascular plasticity involving the rapid envelopment of emboli by endothelial membrane projections that subsequently form a new vessel wall. This was followed by the formation of an endothelial opening through which emboli translocated into the perivascular parenchyma. The rate of embolus extravasation was significantly decreased by pharmacological inhibition of matrix metalloproteinase 2/9 activity. In aged mice, extravasation was markedly delayed, resulting in persistent tissue hypoxia, synaptic damage and cell death. Alterations in the efficiency of the protective mechanism that we have identified may have important implications in microvascular pathology, stroke recovery and age-related cognitive decline.
Asunto(s)
Encéfalo/irrigación sanguínea , Encéfalo/fisiología , Circulación Cerebrovascular/fisiología , Embolia/patología , Microvasos/citología , Microvasos/fisiología , Envejecimiento/fisiología , Animales , Coagulación Sanguínea , Encéfalo/citología , Arterias Carótidas/citología , Arterias Carótidas/fisiología , Muerte Celular , Hipoxia de la Célula , Línea Celular , Estructuras de la Membrana Celular/metabolismo , Estructuras de la Membrana Celular/ultraestructura , Colesterol/metabolismo , Dendritas/metabolismo , Células Endoteliales/citología , Endotelio Vascular/citología , Endotelio Vascular/fisiología , Endotelio Vascular/ultraestructura , Fibrina/metabolismo , Fibrinógeno/metabolismo , Humanos , Ratones , Microesferas , Sinapsis/metabolismo , Sinapsis/patología , Trombina/metabolismoRESUMEN
PURPOSE: To assess the accuracy of best-corrected visual acuity (BCVA) measured by non-ophthalmic emergency department (ED) staff with a standard Snellen chart versus an automated application (app) on a handheld smartphone (Paxos Checkup, San Francisco, CA, USA). METHODS: The study included 128 subjects who presented to the Stanford Hospital ED for whom the ED requested an ophthalmology consultation. We conducted the study in two phases. During phase 1 of the study, ED staff tested patient BCVA using a standard Snellen test at 20 feet. During phase 2 of the study, ED staff tested patient near BCVA using the app. During both phases, ophthalmologists measured BCVA with a Rosenbaum near chart, which was treated as the gold standard. ED BCVA measurements were benchmarked prospectively against ophthalmologists' measurements and converted to logMAR. RESULTS: ED logMAR BCVA was 0.21 ± 0.35 (approximately 2 Snellen lines difference ± 3 Snellen lines) higher than that of ophthalmologists when ED staff used a Snellen chart (p = .0.00003). ED BCVA was 0.06 ± 0.40 (less than 1 Snellen line ± 4 Snellen lines) higher when ED staff used the app (p = 0.246). Inter-observer difference was therefore smaller by more than 1 line (0.15 logMAR) with the app (p = 0.046). CONCLUSIONS: BCVA measured by non-ophthalmic ED staff with an app was more accurate than with a Snellen chart. Automated apps may provide a means to standardize and improve the efficiency of ED ophthalmologic care.
Asunto(s)
Personal de Salud/normas , Oftalmólogos/normas , Teléfono Inteligente/normas , Pruebas de Visión/normas , Agudeza Visual/fisiología , Adulto , Anciano , Servicios Médicos de Urgencia , Femenino , Humanos , Masculino , Persona de Mediana Edad , Aplicaciones Móviles , Estudios Prospectivos , Reproducibilidad de los Resultados , Pruebas de Visión/instrumentación , Recursos HumanosRESUMEN
With the progression of diabetic retinopathy (DR) from the non-proliferative (NPDR) to proliferative (PDR) stage, the possibility of vision impairment increases significantly. Therefore, it is clinically important to detect the progression to PDR stage for proper intervention. We propose a segmentation-assisted DR classification methodology, that builds on (and improves) current methods by using a fully convolutional network (FCN) to segment retinal neovascularizations (NV) in retinal images prior to image classification. This study utilizes the Kaggle EyePacs dataset, containing retinal photographs from patients with varying degrees of DR (mild, moderate, severe NPDR and PDR. Two graders annotated the NV (a board-certified ophthalmologist and a trained medical student). Segmentation was performed by training an FCN to locate neovascularization on 669 retinal fundus photographs labeled with PDR status according to NV presence. The trained segmentation model was used to locate probable NV in images from the classification dataset. Finally, a CNN was trained to classify the combined images and probability maps into categories of PDR. The mean accuracy of segmentation-assisted classification was 87.71% on the test set (SD = 7.71%). Segmentation-assisted classification of PDR achieved accuracy that was 7.74% better than classification alone. Our study shows that segmentation assistance improves identification of the most severe stage of diabetic retinopathy and has the potential to improve deep learning performance in other imaging problems with limited data availability.
RESUMEN
BACKGROUND: Data drift can negatively impact the performance of machine learning algorithms (MLAs) that were trained on historical data. As such, MLAs should be continuously monitored and tuned to overcome the systematic changes that occur in the distribution of data. In this paper, we study the extent of data drift and provide insights about its characteristics for sepsis onset prediction. This study will help elucidate the nature of data drift for prediction of sepsis and similar diseases. This may aid with the development of more effective patient monitoring systems that can stratify risk for dynamic disease states in hospitals. METHODS: We devise a series of simulations that measure the effects of data drift in patients with sepsis, using electronic health records (EHR). We simulate multiple scenarios in which data drift may occur, namely the change in the distribution of the predictor variables (covariate shift), the change in the statistical relationship between the predictors and the target (concept shift), and the occurrence of a major healthcare event (major event) such as the COVID-19 pandemic. We measure the impact of data drift on model performances, identify the circumstances that necessitate model retraining, and compare the effects of different retraining methodologies and model architecture on the outcomes. We present the results for two different MLAs, eXtreme Gradient Boosting (XGB) and Recurrent Neural Network (RNN). RESULTS: Our results show that the properly retrained XGB models outperform the baseline models in all simulation scenarios, hence signifying the existence of data drift. In the major event scenario, the area under the receiver operating characteristic curve (AUROC) at the end of the simulation period is 0.811 for the baseline XGB model and 0.868 for the retrained XGB model. In the covariate shift scenario, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.853 and 0.874 respectively. In the concept shift scenario and under the mixed labeling method, the retrained XGB models perform worse than the baseline model for most simulation steps. However, under the full relabeling method, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.852 and 0.877 respectively. The results for the RNN models were mixed, suggesting that retraining based on a fixed network architecture may be inadequate for an RNN. We also present the results in the form of other performance metrics such as the ratio of observed to expected probabilities (calibration) and the normalized rate of positive predictive values (PPV) by prevalence, referred to as lift, at a sensitivity of 0.8. CONCLUSION: Our simulations reveal that retraining periods of a couple of months or using several thousand patients are likely to be adequate to monitor machine learning models that predict sepsis. This indicates that a machine learning system for sepsis prediction will probably need less infrastructure for performance monitoring and retraining compared to other applications in which data drift is more frequent and continuous. Our results also show that in the event of a concept shift, a full overhaul of the sepsis prediction model may be necessary because it indicates a discrete change in the definition of sepsis labels, and mixing the labels for the sake of incremental training may not produce the desired results.
Asunto(s)
COVID-19 , Enfermedades Transmisibles , Sepsis , Humanos , Pandemias , COVID-19/diagnóstico , Sepsis/diagnóstico , Aprendizaje AutomáticoRESUMEN
Respiratory syncytial virus (RSV) causes millions of infections among children in the US each year and can cause severe disease or death. Infections that are not promptly detected can cause outbreaks that put other hospitalized patients at risk. No tools besides diagnostic testing are available to rapidly and reliably predict RSV infections among hospitalized patients. We conducted a retrospective study from pediatric electronic health record (EHR) data and built a machine learning model to predict whether a patient will test positive to RSV by nucleic acid amplification test during their stay. Our model demonstrated excellent discrimination with an area under the receiver-operating curve of 0.919, a sensitivity of 0.802, and specificity of 0.876. Our model can help clinicians identify patients who may have RSV infections rapidly and cost-effectively. Successfully integrating this model into routine pediatric inpatient care may assist efforts in patient care and infection control.
RESUMEN
Background: Data drift can negatively impact the performance of machine learning algorithms (MLAs) that were trained on historical data. As such, MLAs should be continuously monitored and tuned to overcome the systematic changes that occur in the distribution of data. In this paper, we study the extent of data drift and provide insights about its characteristics for sepsis onset prediction. This study will help elucidate the nature of data drift for prediction of sepsis and similar diseases. This may aid with the development of more effective patient monitoring systems that can stratify risk for dynamic disease states in hospitals. Methods: We devise a series of simulations that measure the effects of data drift in patients with sepsis. We simulate multiple scenarios in which data drift may occur, namely the change in the distribution of the predictor variables (covariate shift), the change in the statistical relationship between the predictors and the target (concept shift), and the occurrence of a major healthcare event (major event) such as the COVID-19 pandemic. We measure the impact of data drift on model performances, identify the circumstances that necessitate model retraining, and compare the effects of different retraining methodologies and model architecture on the outcomes. We present the results for two different MLAs, eXtreme Gradient Boosting (XGB) and Recurrent Neural Network (RNN). Results: Our results show that the properly retrained XGB models outperform the baseline models in all simulation scenarios, hence signifying the existence of data drift. In the major event scenario, the area under the receiver operating characteristic curve (AUROC) at the end of the simulation period is 0.811 for the baseline XGB model and 0.868 for the retrained XGB model. In the covariate shift scenario, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.853 and 0.874 respectively. In the concept shift scenario and under the mixed labeling method, the retrained XGB models perform worse than the baseline model for most simulation steps. However, under the full relabeling method, the AUROC at the end of the simulation period for the baseline and retrained XGB models is 0.852 and 0.877 respectively. The results for the RNN models were mixed, suggesting that retraining based on a fixed network architecture may be inadequate for an RNN. We also present the results in the form of other performance metrics such as the ratio of observed to expected probabilities (calibration) and the normalized rate of positive predictive values (PPV) by prevalence, referred to as lift, at a sensitivity of 0.8. Conclusion: Our simulations reveal that retraining periods of a couple of months or using several thousand patients are likely to be adequate to monitor machine learning models that predict sepsis. This indicates that a machine learning system for sepsis prediction will probably need less infrastructure for performance monitoring and retraining compared to other applications in which data drift is more frequent and continuous. Our results also show that in the event of a concept shift, a full overhaul of the sepsis prediction model may be necessary because it indicates a discrete change in the definition of sepsis labels, and mixing the labels for the sake of incremental training may not produce the desired results.
RESUMEN
BACKGROUND: Acute respiratory distress syndrome (ARDS) is a condition that is often considered to have broad and subjective diagnostic criteria and is associated with significant mortality and morbidity. Early and accurate prediction of ARDS and related conditions such as hypoxemia and sepsis could allow timely administration of therapies, leading to improved patient outcomes. OBJECTIVE: The aim of this study is to perform an exploration of how multilabel classification in the clinical setting can take advantage of the underlying dependencies between ARDS and related conditions to improve early prediction of ARDS in patients. METHODS: The electronic health record data set included 40,703 patient encounters from 7 hospitals from April 20, 2018, to March 17, 2021. A recurrent neural network (RNN) was trained using data from 5 hospitals, and external validation was conducted on data from 2 hospitals. In addition to ARDS, 12 target labels for related conditions such as sepsis, hypoxemia, and COVID-19 were used to train the model to classify a total of 13 outputs. As a comparator, XGBoost models were developed for each of the 13 target labels. Model performance was assessed using the area under the receiver operating characteristic curve. Heat maps to visualize attention scores were generated to provide interpretability to the neural networks. Finally, cluster analysis was performed to identify potential phenotypic subgroups of patients with ARDS. RESULTS: The single RNN model trained to classify 13 outputs outperformed the individual XGBoost models for ARDS prediction, achieving an area under the receiver operating characteristic curve of 0.842 on the external test sets. Models trained on an increasing number of tasks resulted in improved performance. Earlier prediction of ARDS nearly doubled the rate of in-hospital survival. Cluster analysis revealed distinct ARDS subgroups, some of which had similar mortality rates but different clinical presentations. CONCLUSIONS: The RNN model presented in this paper can be used as an early warning system to stratify patients who are at risk of developing one of the multiple risk outcomes, hence providing practitioners with the means to take early action.
RESUMEN
Diagnosis and appropriate intervention for myocardial infarction (MI) are time-sensitive but rely on clinical measures that can be progressive and initially inconclusive, underscoring the need for an accurate and early predictor of MI to support diagnostic and clinical management decisions. The objective of this study was to develop a machine learning algorithm (MLA) to predict MI diagnosis based on electronic health record data (EHR) readily available during Emergency Department assessment. An MLA was developed using retrospective patient data. The MLA used patient data as they became available in the first 3 h of care to predict MI diagnosis (defined by International Classification of Diseases, 10th revision code) at any time during the encounter. The MLA obtained an area under the receiver operating characteristic curve of 0.87, sensitivity of 87% and specificity of 70%, outperforming the comparator scoring systems TIMI and GRACE on all metrics. An MLA can synthesize complex EHR data to serve as a clinically relevant risk stratification tool for MI.
RESUMEN
Objective: In the wake of COVID-19, the United States (U.S.) developed a three stage plan to outline the parameters to determine when states may reopen businesses and ease travel restrictions. The guidelines also identify subpopulations of Americans deemed to be at high risk for severe disease should they contract COVID-19. These guidelines were based on population level demographics, rather than individual-level risk factors. As such, they may misidentify individuals at high risk for severe illness, and may therefore be of limited use in decisions surrounding resource allocation to vulnerable populations. The objective of this study was to evaluate a machine learning algorithm for prediction of serious illness due to COVID-19 using inpatient data collected from electronic health records. Methods: The algorithm was trained to identify patients for whom a diagnosis of COVID-19 was likely to result in hospitalization, and compared against four U.S. policy-based criteria: age over 65; having a serious underlying health condition; age over 65 or having a serious underlying health condition; and age over 65 and having a serious underlying health condition. Results: This algorithm identified 80% of patients at risk for hospitalization due to COVID-19, versus 62% identified by government guidelines. The algorithm also achieved a high specificity of 95%, outperforming government guidelines. Conclusions: This algorithm may identify individuals likely to require hospitalization should they contract COVID-19. This information may be useful to guide vaccine distribution, anticipate hospital resource needs, and assist health care policymakers to make care decisions in a more principled manner.
RESUMEN
BACKGROUND: A high number of patients who are hospitalized with COVID-19 develop acute respiratory distress syndrome (ARDS). OBJECTIVE: In response to the need for clinical decision support tools to help manage the next pandemic during the early stages (ie, when limited labeled data are present), we developed machine learning algorithms that use semisupervised learning (SSL) techniques to predict ARDS development in general and COVID-19 populations based on limited labeled data. METHODS: SSL techniques were applied to 29,127 encounters with patients who were admitted to 7 US hospitals from May 1, 2019, to May 1, 2021. A recurrent neural network that used a time series of electronic health record data was applied to data that were collected when a patient's peripheral oxygen saturation level fell below the normal range (<97%) to predict the subsequent development of ARDS during the remaining duration of patients' hospital stay. Model performance was assessed with the area under the receiver operating characteristic curve and area under the precision recall curve of an external hold-out test set. RESULTS: For the whole data set, the median time between the first peripheral oxygen saturation measurement of <97% and subsequent respiratory failure was 21 hours. The area under the receiver operating characteristic curve for predicting subsequent ARDS development was 0.73 when the model was trained on a labeled data set of 6930 patients, 0.78 when the model was trained on the labeled data set that had been augmented with the unlabeled data set of 16,173 patients by using SSL techniques, and 0.84 when the model was trained on the entire training set of 23,103 labeled patients. CONCLUSIONS: In the context of using time-series inpatient data and a careful model training design, unlabeled data can be used to improve the performance of machine learning models when labeled data for predicting ARDS development are scarce or expensive.
RESUMEN
PURPOSE: Coronavirus disease-2019 (COVID-19) continues to be a global threat and remains a significant cause of hospitalizations. Recent clinical guidelines have supported the use of corticosteroids or remdesivir in the treatment of COVID-19. However, uncertainty remains about which patients are most likely to benefit from treatment with either drug; such knowledge is crucial for avoiding preventable adverse effects, minimizing costs, and effectively allocating resources. This study presents a machine-learning system with the capacity to identify patients in whom treatment with a corticosteroid or remdesivir is associated with improved survival time. METHODS: Gradient-boosted decision-tree models used for predicting treatment benefit were trained and tested on data from electronic health records dated between December 18, 2019, and October 18, 2020, from adult patients (age ≥18 years) with COVID-19 in 10 US hospitals. Models were evaluated for performance in identifying patients with longer survival times when treated with a corticosteroid versus remdesivir. Fine and Gray proportional-hazards models were used for identifying significant findings in treated and nontreated patients, in a subset of patients who received supplemental oxygen, and in patients identified by the algorithm. Inverse probability-of-treatment weights were used to adjust for confounding. Models were trained and tested separately for each treatment. FINDINGS: Data from 2364 patients were included, with men comprising slightly more than 50% of the sample; 893 patients were treated with remdesivir, and 1471 were treated with a corticosteroid. After adjustment for confounding, neither corticosteroids nor remdesivir use was associated with increased survival time in the overall population or in the subpopulation that received supplemental oxygen. However, in the populations identified by the algorithms, both corticosteroids and remdesivir were significantly associated with an increase in survival time, with hazard ratios of 0.56 and 0.40, respectively (both, P = 0.04). IMPLICATIONS: Machine-learning methods have the capacity to identify hospitalized patients with COVID-19 in whom treatment with a corticosteroid or remdesivir is associated with an increase in survival time. These methods may help to improve patient outcomes and allocate resources during the COVID-19 crisis.
Asunto(s)
Adenosina Monofosfato/análogos & derivados , Corticoesteroides , Alanina/análogos & derivados , Antivirales , Tratamiento Farmacológico de COVID-19 , Aprendizaje Automático , Adenosina Monofosfato/uso terapéutico , Adolescente , Corticoesteroides/uso terapéutico , Adulto , Anciano , Anciano de 80 o más Años , Alanina/uso terapéutico , Antivirales/uso terapéutico , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
BACKGROUND: The COVID-19 pandemic remains a significant global threat. However, despite urgent need, there remains uncertainty surrounding best practices for pharmaceutical interventions to treat COVID-19. In particular, conflicting evidence has emerged surrounding the use of hydroxychloroquine and azithromycin, alone or in combination, for COVID-19. The COVID-19 Evidence Accelerator convened by the Reagan-Udall Foundation for the FDA, in collaboration with Friends of Cancer Research, assembled experts from the health systems research, regulatory science, data science, and epidemiology to participate in a large parallel analysis of different data sets to further explore the effectiveness of these treatments. METHODS: Electronic health record (EHR) and claims data were extracted from seven separate databases. Parallel analyses were undertaken on data extracted from each source. Each analysis examined time to mortality in hospitalized patients treated with hydroxychloroquine, azithromycin, and the two in combination as compared to patients not treated with either drug. Cox proportional hazards models were used, and propensity score methods were undertaken to adjust for confounding. Frequencies of adverse events in each treatment group were also examined. RESULTS: Neither hydroxychloroquine nor azithromycin, alone or in combination, were significantly associated with time to mortality among hospitalized COVID-19 patients. No treatment groups appeared to have an elevated risk of adverse events. CONCLUSION: Administration of hydroxychloroquine, azithromycin, and their combination appeared to have no effect on time to mortality in hospitalized COVID-19 patients. Continued research is needed to clarify best practices surrounding treatment of COVID-19.
Asunto(s)
Antivirales/uso terapéutico , Azitromicina/uso terapéutico , Tratamiento Farmacológico de COVID-19 , Hidroxicloroquina/uso terapéutico , Pandemias/prevención & control , Manejo de Datos/métodos , Quimioterapia Combinada/métodos , Femenino , Hospitalización , Humanos , Masculino , SARS-CoV-2/efectos de los fármacosRESUMEN
OBJECTIVES: Rechargeable spinal cord stimulation (RSCS) systems have been advocated as a way to reduce replacement surgeries, overall costs, and the morbidity of therapy. However, little data exist as to patients' experiences with these devices, which require more care and maintenance than prior primary cell systems. We analyzed patient experiences with RSCS. METHODS: Thirty-five patients with implanted RSCS systems completed a survey regarding their use of the system, their experiences with recharging, and their perspectives on the device. RESULTS: Patients reported recharging an average of 5.2 times per month for 2.3 hours each time. Overall, 23.3% of recharging attempts were problematic. There was great variability in the length, frequency, and ease of recharging RSCS systems. These factors determined the patients' level of satisfaction. CONCLUSIONS: RSCS systems benefit most patients. However, in some patients, the lifestyle costs of recharging may not make RSCS an appropriate means of pain management. Several areas of improvement exist for the design of future devices.
RESUMEN
RATIONALE: Prediction of patients at risk for mortality can help triage patients and assist in resource allocation. OBJECTIVES: Develop and evaluate a machine learning-based algorithm which accurately predicts mortality in COVID-19, pneumonia, and mechanically ventilated patients. METHODS: Retrospective study of 53,001 total ICU patients, including 9166 patients with pneumonia and 25,895 mechanically ventilated patients, performed on the MIMIC dataset. An additional retrospective analysis was performed on a community hospital dataset containing 114 patients positive for SARS-COV-2 by PCR test. The outcome of interest was in-hospital patient mortality. RESULTS: When trained and tested on the MIMIC dataset, the XGBoost predictor obtained area under the receiver operating characteristic (AUROC) values of 0.82, 0.81, 0.77, and 0.75 for mortality prediction on mechanically ventilated patients at 12-, 24-, 48-, and 72- hour windows, respectively, and AUROCs of 0.87, 0.78, 0.77, and 0.734 for mortality prediction on pneumonia patients at 12-, 24-, 48-, and 72- hour windows, respectively. The predictor outperformed the qSOFA, MEWS and CURB-65 risk scores at all prediction windows. When tested on the community hospital dataset, the predictor obtained AUROCs of 0.91, 0.90, 0.86, and 0.87 for mortality prediction on COVID-19 patients at 12-, 24-, 48-, and 72- hour windows, respectively, outperforming the qSOFA, MEWS and CURB-65 risk scores at all prediction windows. CONCLUSIONS: This machine learning-based algorithm is a useful predictive tool for anticipating patient mortality at clinically useful timepoints, and is capable of accurate mortality prediction for mechanically ventilated patients as well as those diagnosed with pneumonia and COVID-19.
RESUMEN
Therapeutic agents for the novel coronavirus disease 2019 (COVID-19) have been proposed, but evidence supporting their use is limited. A machine learning algorithm was developed in order to identify a subpopulation of COVID-19 patients for whom hydroxychloroquine was associated with improved survival; this population might be relevant for study in a clinical trial. A pragmatic trial was conducted at six United States hospitals. We enrolled COVID-19 patients that were admitted between 10 March and 4 June 2020. Treatment was not randomized. The study endpoint was mortality; discharge was a competing event. Hazard ratios were obtained on the entire population, and on the subpopulation indicated by the algorithm as suitable for treatment. A total of 290 patients were enrolled. In the subpopulation that was identified by the algorithm, hydroxychloroquine was associated with a statistically significant (p = 0.011) increase in survival (adjusted hazard ratio 0.29, 95% confidence interval (CI) 0.11-0.75). Adjusted survival among the algorithm indicated patients was 82.6% in the treated arm and 51.2% in the arm not treated. No association between treatment and mortality was observed in the general population. A 31% increase in survival at the end of the study was observed in a population of COVID-19 patients that were identified by a machine learning algorithm as having a better outcome with hydroxychloroquine treatment. Precision medicine approaches may be useful in identifying a subpopulation of COVID-19 patients more likely to be proven to benefit from hydroxychloroquine treatment in a clinical trial.
RESUMEN
BACKGROUND: Currently, physicians are limited in their ability to provide an accurate prognosis for COVID-19 positive patients. Existing scoring systems have been ineffective for identifying patient decompensation. Machine learning (ML) may offer an alternative strategy. A prospectively validated method to predict the need for ventilation in COVID-19 patients is essential to help triage patients, allocate resources, and prevent emergency intubations and their associated risks. METHODS: In a multicenter clinical trial, we evaluated the performance of a machine learning algorithm for prediction of invasive mechanical ventilation of COVID-19 patients within 24 h of an initial encounter. We enrolled patients with a COVID-19 diagnosis who were admitted to five United States health systems between March 24 and May 4, 2020. RESULTS: 197 patients were enrolled in the REspirAtory Decompensation and model for the triage of covid-19 patients: a prospective studY (READY) clinical trial. The algorithm had a higher diagnostic odds ratio (DOR, 12.58) for predicting ventilation than a comparator early warning system, the Modified Early Warning Score (MEWS). The algorithm also achieved significantly higher sensitivity (0.90) than MEWS, which achieved a sensitivity of 0.78, while maintaining a higher specificity (p < 0.05). CONCLUSIONS: In the first clinical trial of a machine learning algorithm for ventilation needs among COVID-19 patients, the algorithm demonstrated accurate prediction of the need for mechanical ventilation within 24 h. This algorithm may help care teams effectively triage patients and allocate resources. Further, the algorithm is capable of accurately identifying 16% more patients than a widely used scoring system while minimizing false positive results.
Asunto(s)
Betacoronavirus , Técnicas de Laboratorio Clínico/métodos , Infecciones por Coronavirus/diagnóstico , Infecciones por Coronavirus/fisiopatología , Aprendizaje Automático , Neumonía Viral/diagnóstico , Neumonía Viral/fisiopatología , Insuficiencia Respiratoria/diagnóstico , Insuficiencia Respiratoria/fisiopatología , Adulto , Anciano , Anciano de 80 o más Años , Algoritmos , COVID-19 , Prueba de COVID-19 , Técnicas de Laboratorio Clínico/estadística & datos numéricos , Biología Computacional , Infecciones por Coronavirus/tratamiento farmacológico , Infecciones por Coronavirus/terapia , Femenino , Humanos , Masculino , Persona de Mediana Edad , Pandemias , Neumonía Viral/terapia , Pronóstico , Estudios Prospectivos , Respiración Artificial , Insuficiencia Respiratoria/terapia , SARS-CoV-2 , Sensibilidad y Especificidad , Triaje/métodos , Triaje/estadística & datos numéricos , Estados Unidos/epidemiología , Tratamiento Farmacológico de COVID-19RESUMEN
Diabetic retinopathy is a leading cause of blindness among working-age adults. Early detection of this condition is critical for good prognosis. In this paper, we demonstrate the use of convolutional neural networks (CNNs) on color fundus images for the recognition task of diabetic retinopathy staging. Our network models achieved test metric performance comparable to baseline literature results, with validation sensitivity of 95%. We additionally explored multinomial classification models, and demonstrate that errors primarily occur in the misclassification of mild disease as normal due to the CNNs inability to detect subtle disease features. We discovered that preprocessing with contrast limited adaptive histogram equalization and ensuring dataset fidelity by expert verification of class labels improves recognition of subtle features. Transfer learning on pretrained GoogLeNet and AlexNet models from ImageNet improved peak test set accuracies to 74.5%, 68.8%, and 57.2% on 2-ary, 3-ary, and 4-ary classification models, respectively.
RESUMEN
Purpose: To develop an automated method of localizing and discerning multiple types of findings in retinal images using a limited set of training data without hard-coded feature extraction as a step toward generalizing these methods to rare disease detection in which a limited number of training data are available. Methods: Two ophthalmologists verified 243 retinal images, labeling important subsections of the image to generate 1324 image patches containing either hemorrhages, microaneurysms, exudates, retinal neovascularization, or normal-appearing structures from the Kaggle dataset. These image patches were used to train one standard convolutional neural network to predict the presence of these five classes. A sliding window method was used to generate probability maps across the entire image. Results: The method was validated on the eOphta dataset of 148 whole retinal images for microaneurysms and 47 for exudates. A pixel-wise classification of the area under the curve of the receiver operating characteristic of 0.94 and 0.95, as well as a lesion-wise area under the precision recall curve of 0.86 and 0.64, was achieved for microaneurysms and exudates, respectively. Conclusions: Regionally trained convolutional neural networks can generate lesion-specific probability maps able to detect and distinguish between subtle pathologic lesions with only a few hundred training examples per lesion.
Asunto(s)
Interpretación de Imagen Asistida por Computador , Redes Neurales de la Computación , Enfermedades de la Retina/diagnóstico por imagen , Algoritmos , Exudados y Transudados , Humanos , Aprendizaje Automático , Probabilidad , Curva ROC , Reproducibilidad de los ResultadosRESUMEN
Objective: Deep learning has become a promising approach for automated support for clinical diagnosis. When medical data samples are limited, collaboration among multiple institutions is necessary to achieve high algorithm performance. However, sharing patient data often has limitations due to technical, legal, or ethical concerns. In this study, we propose methods of distributing deep learning models as an attractive alternative to sharing patient data. Methods: We simulate the distribution of deep learning models across 4 institutions using various training heuristics and compare the results with a deep learning model trained on centrally hosted patient data. The training heuristics investigated include ensembling single institution models, single weight transfer, and cyclical weight transfer. We evaluated these approaches for image classification in 3 independent image collections (retinal fundus photos, mammography, and ImageNet). Results: We find that cyclical weight transfer resulted in a performance that was comparable to that of centrally hosted patient data. We also found that there is an improvement in the performance of cyclical weight transfer heuristic with a high frequency of weight transfer. Conclusions: We show that distributing deep learning models is an effective alternative to sharing patient data. This finding has implications for any collaborative deep learning study.
Asunto(s)
Aprendizaje Profundo , Diagnóstico por Imagen , Redes de Comunicación de Computadores , Humanos , Registro Médico Coordinado , Redes Neurales de la ComputaciónRESUMEN
PURPOSE: The purpose of this study was to evaluate the long-term efficacy of phototherapeutic keratectomy (PTK) in treating epithelial basement membrane dystrophy (EBMD). METHODS: Preoperative and postoperative records were reviewed for 58 eyes of 51 patients with >3 months follow-up (range 3-170 months) treated for EBMD with PTK after failure of conservative medical treatment at Byers Eye Institute of Stanford University. Symptoms, clinical findings, and corrected distance visual acuity (CDVA) were assessed. The primary outcome measure was symptomatic recurrence as measured by erosions or visual complaints >3 months after successful PTK. RESULTS: For eyes with visual disturbances (n=30), preoperative CDVA was20/32 (0.24 Log-MAR, SD 0.21) and postoperative CDVA was ~20/25 (0.07 LogMAR, SD 0.12; P<0.0001). Twenty-six eyes (86.7%) responded to treatment, with symptomatic recurrence in 6 eyes (23.1%) at an average of 37.7 months (SD 42.8). For eyes with painful erosions (n=29), preoperative CDVA was ~20/25 (0.12, SD 0.19) and postoperative CDVA was ~20/20 (0.05. SD 0.16; P=0.0785). Twenty-three eyes (79.3%) responded to treatment, with symptomatic recurrence in 3 eyes (13.0%) at an average of 9.7 months (SD 1.5). The probability of being recurrence free after a successful treatment for visual disturbances and erosions at 5 years postoperatively was estimated at 83.0% (95% confidence interval 68.7%-97.0%) and 88.0% (95% confidence interval 65.3%-96.6%), respectively. CONCLUSION: The majority of visual disturbances and painful erosions associated with EBMD respond to PTK. For those with a treatment response, symptomatic relief is maintained over long-term follow-up.