Development of machine learning algorithms for prediction of mortality in spinal epidural abscess
توسعه الگوریتم های یادگیری ماشین برای پیش بینی مرگ و میر در آبسه اپیدورال ستون فقرات-2019
BACKGROUND CONTEXT: In-hospital and short-term mortality in patients with spinal epidural abscess (SEA) remains unacceptably high despite diagnostic and therapeutic advancements. Forecasting this potentially avoidable consequence at the time of admission could improve patient management and counseling. Few studies exist to meet this need, and none have explored methodologies such as machine learning. PURPOSE: The purpose of this study was to develop machine learning algorithms for prediction of in-hospital and 90-day postdischarge mortality in SEA. STUDY DESIGN/SETTING: Retrospective, case-control study at two academic medical centers and three community hospitals from 1993 to 2016. PATIENTS SAMPLE: Adult patients with an inpatient admission for radiologically confirmed diagnosis of SEA. OUTCOME MEASURES: In-hospital and 90-day postdischarge mortality. METHODS: Five machine learning algorithms (elastic-net penalized logistic regression, random forest, stochastic gradient boosting, neural network, and support vector machine) were developed and assessed by discrimination, calibration, overall performance, and decision curve analysis. RESULTS: Overall, 1,053 SEA patients were identified in the study, with 134 (12.7%) experiencing in-hospital or 90-day postdischarge mortality. The stochastic gradient boosting model achieved the best performance across discrimination, c-statistic=0.89, calibration, and decision curve analysis. The variables used for prediction of 90-day mortality, ranked by importance, were age, albumin, platelet count, neutrophil to lymphocyte ratio, hemodialysis, active malignancy, and diabetes. The final algorithm was incorporated into a web application available here: https://sorg-apps.shinyapps.io/seamortality/. CONCLUSIONS: Machine learning algorithms show promise on internal validation for prediction of 90-day mortality in SEA. Future studies are needed to externally validate these algorithms inindependent populations.
Keywords: Artificial intelligence | Healthcare | Machine learning | Mortality | Spinal epidural abscess | Spine surgery
Patient Clustering Improves Efficiency of Federated Machine Learning to Predict Mortality and Hospital Stay Time Using Distributed Electronic Medical Records
وشه بندی بیمار باعث افزایش کارآیی یادگیری ماشین فدرال برای پیش بینی مرگ و میر و مدت زمان ماندن بیمارستان با استفاده از سوابق پزشکی الکترونیکی توزیع شده-2019
Electronic medical records (EMRs) support the development of machine learning algorithms for predicting disease incidence, patient response to treatment, and other healthcare events. But so far most algorithms have been centralized, taking little account of the decentralized, non-identically independently distributed (non-IID), and privacy-sensitive characteristics of EMRs that can complicate data collection, sharing and learning. To address this challenge, we introduced a community-based federated machine learning (CBFL) algorithm and evaluated it on non-IID ICU EMRs. Our algorithm clustered the distributed data into clinically meaningful communities that captured similar diagnoses and geographical locations, and learnt one model for each community. Throughout the learning process, the data was kept local at hospitals, while locally-computed results were aggregated on a server. Evaluation results show that CBFL outperformed the baseline federated machine learning (FL) algorithm in terms of Area Under the Receiver Operating Characteristic Curve (ROC AUC), Area Under the Precision-Recall Curve (PR AUC), and communication cost between hospitals and the server. Furthermore, communities’ performance difference could be explained by how dissimilar one community was to others.
Keywords: distributed clustering | autoencoder | federated machine learning | non-IID | critical care
Main factors influencing recovery in MERS Co-V patients using machine learning
عوامل اصلی موثر بر بهبود در بیماران MERS Co-V با استفاده از یادگیری ماشین-2019
Background: Middle East Respiratory Syndrome (MERS) is a major infectious disease which has affectedthe Middle Eastern countries, especially the Kingdom of Saudi Arabia (KSA) since 2012. The high mortalityrate associated with this disease has been a major cause of concern. This paper aims at identifying themajor factors influencing MERS recovery in KSA.Methods: The data used for analysis was collected from the Ministry of Health website, KSA. The impor-tant factors impelling the recovery are found using machine learning. Machine learning models suchas support vector machine, conditional inference tree, naïve Bayes and J48 are modelled to identify theimportant factors. Univariate and multivariate logistic regression analysis is also carried out to identifythe significant factors statistically.Result: The main factors influencing MERS recovery rate are identified as age, pre-existing diseases, sever-ity of disease and whether the patient is a healthcare worker or not. In spite of MERS being a zoonoticdisease, contact with camels is not a major factor influencing recovery.Conclusion: The methods used were able to determine the prime factors influencing MERS recovery. Itcan be comprehended that awareness about symptoms and seeking medical intervention at the onset ofdevelopment of symptoms will make a long way in reducing the mortality rate.
Keywords:MERSInfectious disease | Survival rate | Machine learning | Saudi Arabia
Leveraging Machine Learning Techniques to Forecast Patient Prognosis After Percutaneous Coronary Intervention
تکنیک های یادگیری ماشین برای پیش بینی پیش بینی بیمار پس از مداخله کرونر در رحم-2019
OBJECTIVES This study sought to determine whether machine learning can be used to better identify patients at risk for death or congestive heart failure (CHF) rehospitalization after percutaneous coronary intervention (PCI). BACKGROUND Contemporary risk models for event prediction after PCI have limited predictive ability. Machine learning has the potential to identify complex nonlinear patterns within datasets, improving the predictive power of models. METHODS We evaluated 11,709 distinct patients who underwent 14,349 PCIs between January 2004 and December 2013 in the Mayo Clinic PCI registry. Fifty-two demographic and clinical parameters known at the time of admission were used to predict in-hospital mortality and 358 additional variables available at discharge were examined to identify patients at risk for CHF readmission. For each event, we trained a random forest regression model (i.e., machine learning) to estimate the time-to-event. Eight-fold cross-validation was used to estimate model performance. We used the predicted time-to-event as a score, generated a receiver-operating characteristic curve, and calculated the area under the curve (AUC). Model performance was then compared with a logistic regression model using pairwise comparisons of AUCs and calculation of net reclassification indices. RESULTS The predictive algorithm identified a high-risk cohort representing 2% of all patients who had an in-hospital mortality of 45.5% (95% confidence interval: 43.5% to 47.5%) compared with a risk of 2.1% for the general population (AUC: 0.925; 95% confidence interval: 0.92 to 0.93). Advancing age, CHF, and shock on presentation were the leading predictors for the outcome. A high-risk group representing 1% of all patients was identified with 30-day CHF rehospitalization of 8.1% (95% confidence interval: 6.3% to 10.2%). Random forest regression outperformed logistic regression for predicting 30-day CHF readmission (AUC: 0.90 vs. 0.85; p ¼ 0.003; net reclassification improvement: 5.14%) and 180-day cardiovascular death (AUC: 0.88 vs. 0.81; p ¼ 0.02; net reclassification improvement: 0.02%). CONCLUSIONS Random forest regression models (machine learning) were more predictive and discriminative than standard regression methods at identifying patients at risk for 180-day cardiovascular mortality and 30-day CHF rehospitalization, but not in-hospital mortality. Machine learning was effective at identifying subgroups at high risk for postprocedure mortality and readmission. (J Am Coll Cardiol Intv 2019;12:1304–11) © 2019 Published by Elsevier on behalf of the American College of Cardiology Foundation.
Machine Learning Prediction Models for In-Hospital Mortality After Transcatheter Aortic Valve Replacement
یادگیری ماشین مدل های پیش بینی شده برای مرگ در بیمارستان پس از جایگزینی ترانس دریچه آئورت-2019
OBJECTIVES This study sought to develop and compare an array of machine learning methods to predict in-hospital mortality after transcatheter aortic valve replacement (TAVR) in the United States. BACKGROUND Existing risk prediction tools for in-hospital complications in patients undergoing TAVR have been designed using statistical modeling approaches and have certain limitations. METHODS Patient data were obtained from the National Inpatient Sample database from 2012 to 2015. The data were randomly divided into a development cohort (n ¼ 7,615) and a validation cohort (n ¼ 3,268). Logistic regression, artificial neural network, naive Bayes, and random forest machine learning algorithms were applied to obtain in-hospital mortality prediction models. RESULTS A total of 10,883 TAVRs were analyzed in our study. The overall in-hospital mortality was 3.6%. Overall, prediction models’ performance measured by area under the curve were good (>0.80). The best model was obtained by logistic regression (area under the curve: 0.92; 95% confidence interval: 0.89 to 0.95). Most obtained models plateaued after introducing 10 variables. Acute kidney injury was the main predictor of in-hospital mortality ranked with the highest mean importance in all the models. The National Inpatient Sample TAVR score showed the best discrimination among available TAVR prediction scores. CONCLUSIONS Machine learning methods can generate robust models to predict in-hospital mortality for TAVR. The National Inpatient Sample TAVR score should be considered for prognosis and shared decision making in TAVR patients. (J Am Coll Cardiol Intv 2019;12:1328–38) © 2019 by the American College of Cardiology Foundation.
ISeeU: Visually interpretable deep learning for mortality prediction inside the ICU
ISeeU: یادگیری عمیق قابل تفسیر برای پیش بینی مرگ و میر در بخش مراقبت های ویژه-2019
To improve the performance of Intensive Care Units (ICUs), the field of bio-statistics has developed scores which try to predict the likelihood of negative outcomes. These help evaluate the effectiveness of treatments and clinical practice, and also help to identify patients with unexpected outcomes. However, they have been shown by several studies to offer sub-optimal performance. Alternatively, Deep Learning offers state of the art capabilities in certain prediction tasks and research suggests deep neural networks are able to outperform traditional techniques. Nevertheless, a main impediment for the adoption of Deep Learning in healthcare is its reduced interpretability, for in this field it is crucial to gain insight into the why of predictions, to assure that models are actually learning relevant features instead of spurious correlations. To address this, we propose a deep multiscale convolutional architecture trained on the Medical Information Mart for Intensive Care III (MIMIC-III) for mortality prediction, and the use of concepts from coalitional game theory to construct visual explanations aimed to show how important these inputs are deemed by the network. Results show our model attains a ROC AUC of 0.8735 (± 0.0025) which is competitive with the state of the art of Deep Learning mortality models trained on MIMIC-III data, while remaining interpretable. Supporting code can be found at https://github.com/ williamcaicedo/ISeeU.
Keywords: Deep learning | MIMIC-III | ICU | Shapley Values
Conservation region finding for influenza A viruses by machine learning methods of N-linked glycosylation sites and B-cell epitopes
یافتن منطقه حفاظت از ویروس های آنفلوانزا A با استفاده از روش های یادگیری ماشینی سایت های گلیکوزیلاسیون مرتبط با N و اپی توپ های سلول B-2019
Influenza type A, a serious infectious disease of the human respiratory tract, poses an enormous threat to human health worldwide. It leads to high mortality rates in poultry, pigs, and humans. The primary target identity regions for the human immune system are hemagglutinin (HA) and neuraminidase (NA), two surface proteins of the influenza A virus. Research and development of vaccines is highly complex because the influenza A virus evolves rapidly. This study focused on three genetic features of viral surface proteins: ribonucleic acid (RNA) sequence conservation, linear B-cell epitopes, and N-linked glycosylation. On the basis of these three properties, we analyzed 12,832 HA and 9487 NA protein sequences, which we retrieved from the influenza virus database. We classified the viral surface protein sequences into the 18 HA and 11 NA subtypes that have been identified thus far. Using available analytic tools, we searched for the representative strain of each virus subtype. Furthermore, using machine learning methods, we looked for conservation regions with sequences showing linear B-cell epitopes and N-linked glycosylation. Compared to the prediction of the Immune Epitope Database (IEDB) antibody neutralization response (i.e., screening of antibody sequence regions), in this study, the virus sequence coverage was large and accurate and contained N-linked glycosylation sites. The results of this study proved that we can use the machine learning-based prediction method to solve the problem of vaccine invalidation that occurred during the rapid evolution of the influenza A virus and also as a prevaccine assessment. In addition, the screening fragments can be used as a universal influenza vaccine design reference in the future.
Keywords: Hemagglutinin | Neuraminidase | N-linked glycosylation | Linear B-cell epitope | Machine learning
Deep-learning model for predicting 30-day postoperative mortality
مدل یادگیری عمیق برای پیش بینی مرگ و میر 30 روز بعد از عمل-2019
Background: Postoperative mortality occurs in 1e2% of patients undergoing major inpatient surgery. The currently available prediction tools using summaries of intraoperative data are limited by their inability to reflect shifting risk associated with intraoperative physiological perturbations. We sought to compare similar benchmarks to a deeplearning algorithm predicting postoperative 30-day mortality. Methods: We constructed a multipath convolutional neural network model using patient characteristics, co-morbid conditions, preoperative laboratory values, and intraoperative numerical data from patients undergoing surgery with tracheal intubation at a single medical centre. Data for 60 min prior to a randomly selected time point were utilised. Model performance was compared with a deep neural network, a random forest, a support vector machine, and a logistic regression using predetermined summary statistics of intraoperative data. Results: Of 95 907 patients, 941 (1%) died within 30 days. The multipath convolutional neural network predicted postoperative 30-day mortality with an area under the receiver operating characteristic curve of 0.867 (95% confidence interval [CI]: 0.835e0.899). This was higher than that for the deep neural network (0.825; 95% CI: 0.790e0.860), random forest (0.848; 95% CI: 0.815e0.882), support vector machine (0.836; 95% CI: 0.802e870), and logistic regression (0.837; 95% CI: 0.803e0.871). Conclusions: A deep-learning time-series model improves prediction compared with models with simple summaries of intraoperative data. We have created a model that can be used in real time to detect dynamic changes in a patient’s risk for postoperative mortality.
Keywords: anaesthesiology | deep learning | machine learning | postoperative complications | risk prediction | surgery
A comparative study of deep learning architectures on melanoma detection
مطالعه تطبیقی معماریهای یادگیری عمیق در تشخیص ملانوما-2019
Melanoma is the most aggressive type of skin cancer, which significantly reduces the life expectancy. Early detection of melanoma can reduce the morbidity and mortality associated with skin cancer. Dermoscopic images acquired by dermoscopic instruments are used in computational analysis for skin cancer detection. However, some image quality limitations such as noises, shadows, artefacts exist that could compromise the robustness of the skin image analysis. Hence, developing an automatic intelligent system for skin cancer diagnosis with accurate detection rate is crucial. In this paper, we evaluate the performance of several state-of-the-art convolutional neural networks in dermoscopic images of skin lesions. Our experiment is conducted on a graphics processing unit (GPU) to speed up the training and deployment process. To enhance the quality of images, we employ different pre-processing steps. We also apply data augmentation methodology such as horizontal and vertical flipping techniques to address the class skewness problem. Both pre-processing and data augmentation could help to improve the final accuracy.
Keywords: Cancer classification | Computational diagnosis | Convolutional neural networks | Deep learning | Melanoma detection
Medico-legal considerations and operative vaginal delivery
ملاحظات پزشکی قانونی و زایمان واژینال عملیاتی-2019
Women undergo operative vaginal delivery (OVD) as an alternative to caesarean section when complications arise in the second stage of labour. The perinatal mortality associated with OVD is very low, and most of the perinatal morbidity is minor. However, when serious adverse events occur, such as traumatic birth injury, shoulder dystocia, cerebral palsy and perinatal death, there are medico-legal implications. There is also the potential for litigation in relation to maternal pelvic floor injury, which is increased with OVD. Obstetricians performing and supervising OVDs need to be aware of the potential pitfalls and minimise the risk of adverse outcomes. Given that most obstetricians will be involved in adverse birth-related events, it is important that they are aware of the legal processes that may ensue. It is also important when reviewing adverse OVD-related outcomes that association is differentiated from causation. These issues are addressed in the current chapter with attention drawn to the Montgomery ruling, which redefines the legal standards expected in relation to informed consent.
Keywords: Operative vaginal delivery (OVD) | Serious adverse events | Litigation | Medico-legal | Causation | Montgomery ruling