MIMIC Dataset Research Articles

Accurate and 30-plus days reliable cuffless blood pressure measurements with 9-minutes personal photoplethysmograph data and mixed deduction learning

Cuffless blood pressure (BP) measurements have long been anticipated, and the PPG (Photoplethysmography)-only method is the most promising one since already embedded in many wearable devices. To further meet the clinical accuracy requirements, PPG-only BP predictions with personalized modeling for overcoming personal deviations have been widely studied, but all required tens to hundreds of minutes of personal PPG measurements for training. Moreover, their accurate test periods without calibration practice were not reported. In this work, we collected records of PPG data from our recruited subjects in real-life scenarios instead of relying on the openly available MIMIC dataset obtained from intensive care unit (ICU) patients. Since our objective is commercial application and a substantial reduction in training data, we tailored our model training to closely mimic real-world usage. To achieve this, we developed a training approach that only requires 9-minutes of personal PPG signal recordings and mixed with other PPG data from our recruited 364 subjects. The modeling is conducted with two-channel paired inputs to the convolutional neural network (CNN)-based model, which we called Mixed Deduction Learning (MDL). The test results of 88 samples from 15 subjects, under testing period up to 30-plus days without extra calibration, revealed that MDL meets most of the standards of AAMI, BHS, and IEEE 1708–2014 (for static test only) for BP measurement devices, which indicates MDL’s long-term stability and consistency. Furthermore, we found that the model with two-channel inputs presents a trend of improving performance as the pool of mixed training data increased, while the conventional one-channel input revealed degraded performance. The outperformance of MDL is attributed to many significant features remained in the first CNN layer even when mixing personal 9-minutes data with the other 364 subjects. Consequently, PPG-only with MDL introduces a new avenue for overcoming challenges in training due to personal physiological variations. Given our consideration of real-life usage, this technology can be seamlessly translated to commercial applications.

A Bayesian non-stationary heteroskedastic time series model for multivariate critical care data.

We propose a multivariate GARCH model for non-stationary health time series by modifying the observation-level variance of the standard state space model. The proposed model provides an intuitive and novel way of dealing with heteroskedastic data using the conditional nature of state-space models. We follow the Bayesian paradigm to perform the inference procedure. In particular, we use Markov chain Monte Carlo methods to obtain samples from the resultant posterior distribution. We use the forward filtering backward sampling algorithm to efficiently obtain samples from the posterior distribution of the latent state. The proposed model also handles missing data in a fully Bayesian fashion. We validate our model on synthetic data and analyze a data set obtained from an intensive care unit in a Montreal hospital and the MIMIC dataset. We further show that our proposed models offer better performance, in terms of WAIC than standard state space models. The proposed model provides a new way to model multivariate heteroskedastic non-stationary time series data. Model comparison can then be easily performed using the WAIC.

A nursing note-aware deep neural network for predicting mortality risk after hospital discharge

BackgroundICU readmissions and post-discharge mortality pose significant challenges. Previous studies used EHRs and machine learning models, but mostly focused on structured data. Nursing records contain crucial unstructured information, but their utilization is challenging. Natural language processing (NLP) can extract structured features from clinical text. This study proposes the Crucial Nursing Description Extractor (CNDE) to predict post-ICU discharge mortality rates and identify high-risk patients for unplanned readmission by analyzing electronic nursing records. ObjectiveDeveloped a deep neural network (NurnaNet) with the ability to perceive nursing records, combined with a bio-clinical medicine pre-trained language model (BioClinicalBERT) to analyze the electronic health records (EHRs) in the MIMIC III dataset to predict the death of patients within six month and two year risk. DesignA cohort and system development design was used. Setting(s)Based on data extracted from MIMIC-III, a database of critically ill in the US between 2001 and 2012, the results were analyzed. ParticipantsWe calculated patients' age using admission time and date of birth information from the MIMIC dataset. Patients under 18 or over 89 years old, or who died in the hospital, were excluded. We analyzed 16,973 nursing records from patients' ICU stays. MethodsWe have developed a technology called the Crucial Nursing Description Extractor (CNDE), which extracts key content from text. We use the logarithmic likelihood ratio to extract keywords and combine BioClinicalBERT. We predict the survival of discharged patients after six months and two years and evaluate the performance of the model using precision, recall, the F1-score, the receiver operating characteristic curve (ROC curve), the area under the curve (AUC), and the precision–recall curve (PR curve). ResultsThe research findings indicate that NurnaNet achieved good F1-scores (0.67030, 0.70874) within six months and two years. Compared to using BioClinicalBERT alone, there was an improvement in performance of 2.05 % and 1.08 % for predictions within six months and two years, respectively. ConclusionsCNDE can effectively reduce long-form records and extract key content. NurnaNet has a good F1-score in analyzing the data of nursing records, which helps to identify the risk of death of patients after leaving the hospital and adjust the regular follow-up and treatment plan of relevant medical care as soon as possible.

Intelligent Electrocardiogram Acquisition Via Ubiquitous Photoplethysmography Monitoring.

Recent advances in machine learning, particularly deep neural network architectures, have shown substantial promise in classifying and predicting cardiac abnormalities from electrocardiogram (ECG) data. Such data are rich in information content, typically in morphology and timing, due to the close correlation between cardiac function and the ECG. However, the ECG is usually not measured ubiquitously in a passive manner from consumer devices, and generally requires 'active' sampling whereby the user prompts a device to take an ECG measurement. Conversely, photoplethysmography (PPG) data are typically measured passively by consumer devices, and therefore available for long-period monitoring and suitable in duration for identifying transient cardiac events. However, classifying or predicting cardiac abnormalities from the PPG is very difficult, because it is a peripherally-measured signal. Hence, the use of the PPG for predictive inference is often limited to deriving physiological parameters (heart rate, breathing rate, etc.) or for obvious abnormalities in cardiac timing, such as atrial fibrillation/flutter ("palpitations"). This work aims to combine the best of both worlds: using continuously-monitored, near-ubiquitous PPG to identify periods of sufficient abnormality in the PPG such that prompting the user to take an ECG would be informative of cardiac risk. We propose a dual-convolutional-attention network (DCA-Net) to achieve this ECG-based PPG classification. With DCA-Net, we prove the plausibility of this concept on MIMIC Waveform Database with high performance level (AUROC 0.9 and AUPRC 0.7) and receive satisfactory result when testing the model on an independent dataset (AUROC 0.7 and AUPRC 0.6) which it is not perfectly-matched to the MIMIC dataset.

An Enhanced Autoencoder-based Anomaly Detection Model for time series Data from Wearable Medical Devices.

In today's era of rapidly advancing technologies, such as sensors and the Internet of Things (IoT), and the increasing focus on promoting healthy lifestyles, smart wearable devices play a crucial role in real-time detection and diagnosis of physical health conditions. Through analyzing the multi-featured time series data captured by these devices with multiple sensors, we can uncover hidden diseases and provide timely treatment. Therefore, it is imperative to study an anomaly detection model with robust feature learning and anomaly diagnosis capabilities. To address this need, this paper proposes an enhanced autoencoder-based anomaly detection model for time series data obtained from wearable medical devices. Initially, the model utilizes a convolutional neural network to learn the correlations between multiple features. Subsequently, a long and short-term memory network is employed to capture the sequence correlations, and an multi-head attention mechanism is used to mitigate the performance degradation caused by increasing the sequence length. The residual loss is also used to effectively mitigate the vanishing gradient problem. Finally, the model is evaluated using two widely recognized public datasets: the HeartDisease dataset, which contains information on patients with heart conditions, and the MIMIC dataset, a comprehensive database of de-identified health data related to critical care. The experimental results demonstrate that our model can achieve an accuracy of 95.37% and 95.56% on the two datasets, respectively. Compared to the best performing baseline methods, our model improves 8.6% and 12.3% on the two datasets, respectively. Overall, our model enables efficient analysis of sequential data, effectively captures long-term dependencies, and significantly improves the success rate of early health diagnosis for individuals.

WindowNet: Learnable Windows for Chest X-ray Classification.

Public chest X-ray (CXR) data sets are commonly compressed to a lower bit depth to reduce their size, potentially hiding subtle diagnostic features. In contrast, radiologists apply a windowing operation to the uncompressed image to enhance such subtle features. While it has been shown that windowing improves classification performance on computed tomography (CT) images, the impact of such an operation on CXR classification performance remains unclear. In this study, we show that windowing strongly improves the CXR classification performance of machine learning models and propose WindowNet, a model that learns multiple optimal window settings. Our model achieved an average AUC score of 0.812 compared with the 0.759 score of a commonly used architecture without windowing capabilities on the MIMIC data set.

Identifying causal effects of the clinical sentiment of patients' nursing notes on anticipated fall risk stratification

Stratifying patients with high risks of falling based on assessment with nursing notes is essential for tailoring anticipated fall prevention strategies. However, the average exposure effects of the clinical sentiment polarity (CSP) of nursing notes on the fall risks of patients are still not well understood. Thus, this study proposes a causal inference framework to identify the exposure effect on patients' anticipated fall risks using electronic nursing notes. The augmented inverse probability weighting model is leveraged to estimate the average exposure effect in a quasi-experiment. The experimental data contains 334,000 words of 2,434 nursing notes from the MIMIC dataset. The results show that the fall risk of exposure to the positive CSP is 0.0054 lower than the control group. The contribution of this paper is three-fold. First, the exposure effect of the CSP in the clinical nursing notes is identified with the causal inference method, which augments the Morse fall scale by analyzing the nursing notes. Second, the Pearson correlations between the exposure and the MFS are sensitive to the cut-off of the clinical sentiment score. By contrast, our results show that their impact on the fall risks in the weighting model can be identified (negative effect) when reducing the bias of covariate imbalance. Compared to the risk factors in the Morse fall scale, the CSP takes a scale of 10 for predicting anticipated fall risks. Third, the CSP factor can be extracted from the sentiment lexicons of nursing notes on the patient's fall risks with information processing methods, which contributes to the clinical decision support of anticipated fall prevention.

Transportability of bacterial infection prediction models for critically ill patients.

Bacterial infections (BIs) are common, costly, and potentially life-threatening in critically ill patients. Patients with suspected BIs may require empiric multidrug antibiotic regimens and therefore potentially be exposed to prolonged and unnecessary antibiotics. We previously developed a BI risk model to augment practices and help shorten the duration of unnecessary antibiotics to improve patient outcomes. Here, we have performed a transportability assessment of this BI risk model in 2 tertiary intensive care unit (ICU) settings and a community ICU setting. We additionally explored how simple multisite learning techniques impacted model transportability. Patients suspected of having a community-acquired BI were identified in 3 datasets: Medical Information Mart for Intensive Care III (MIMIC), Northwestern Medicine Tertiary (NM-T) ICUs, and NM "community-based" ICUs. ICU encounters from MIMIC and NM-T datasets were split into 70/30 train and test sets. Models developed on training data were evaluated against the NM-T and MIMIC test sets, as well as NM community validation data. During internal validations, models achieved AUROCs of 0.78 (MIMIC) and 0.81 (NM-T) and were well calibrated. In the external community ICU validation, the NM-T model had robust transportability (AUROC 0.81) while the MIMIC model transported less favorably (AUROC 0.74), likely due to case-mix differences. Multisite learning provided no significant discrimination benefit in internal validation studies but offered more stability during transport across all evaluation datasets. These results suggest that our BI risk models maintain predictive utility when transported to external cohorts. Our findings highlight the importance of performing external model validation on myriad clinically relevant populations prior to implementation.

KD-Informer: A Cuff-Less Continuous Blood Pressure Waveform Estimation Approach Based on Single Photoplethysmography.

Ambulatory blood pressure (BP) monitoring plays a critical role in the early prevention and diagnosis of cardiovascular diseases. However, cuff-based inflatable devices cannot be used for continuous BP monitoring, while pulse transit time or multi-parameter-based methods require more bioelectrodes to acquire electrocardiogram signals. Thus, estimating the BP waveforms only based on photoplethysmography (PPG) signals for continuous BP monitoring has essential clinical values. Nevertheless, extracting useful features from raw PPG signals for fine-grained BP waveform estimation is challenging due to the physiological variation and noise interference. For single PPG analysis utilizing deep learning methods, the previous works depend mainly on stacked convolution operation, which ignores the underlying complementary time-dependent information. Thus, this work presents a novel Transformer-based method with knowledge distillation (KD-Informer) for BP waveform estimation. Meanwhile, we integrate the prior information of PPG patterns, selected by a novel backward elimination algorithm, into the knowledge transfer branch of the KD-Informer. With these strategies, the model can effectively capture the discriminative features through a lightweight architecture during the learning process. Then, we further adopt an effective transfer learning technique to demonstrate the excellent generalization capability of the proposed model using two independent multicenter datasets. Specifically, we first fine-tuned the KD-Informer with a large and high-quality dataset (Mindray dataset) and then transferred the pre-trained model to the target domain (MIMIC dataset). The experimental test results on the MIMIC dataset showed that the KD-Informer exhibited an estimation error of 0.02 ± 5.93 mmHg for systolic BP (SBP) and 0.01 ± 3.87 mmHg for diastolic BP (DBP), which complied with the association for the advancement of medical instrumentation (AAMI) standard. These results demonstrate that the KD-Informer has high reliability and elegant robustness to measure continuous BP waveforms.

Cuff-Less Blood Pressure Prediction Based on Photoplethysmography and Modified ResNet.

Cardiovascular disease (CVD) has become a common health problem of mankind, and the prevalence and mortality of CVD are rising on a year-to-year basis. Blood pressure (BP) is an important physiological parameter of the human body and also an important physiological indicator for the prevention and treatment of CVD. Existing intermittent measurement methods do not fully indicate the real BP status of the human body and cannot get rid of the restraining feeling of a cuff. Accordingly, this study proposed a deep learning network based on the ResNet34 framework for continuous prediction of BP using only the promising PPG signal. The high-quality PPG signals were first passed through a multi-scale feature extraction module after a series of pre-processing to expand the perceptive field and enhance the perception ability on features. Subsequently, useful feature information was then extracted by stacking multiple residual modules with channel attention to increase the accuracy of the model. Lastly, in the training stage, the Huber loss function was adopted to stabilize the iterative process and obtain the optimal solution of the model. On a subset of the MIMIC dataset, the errors of both SBP and DBP predicted by the model met the AAMI standards, while the accuracy of DBP reached Grade A of the BHS standard, and the accuracy of SBP almost reached Grade A of the BHS standard. The proposed method verifies the potential and feasibility of PPG signals combined with deep neural networks in the field of continuous BP monitoring. Furthermore, the method is easy to deploy in portable devices, and it is more consistent with the future trend of wearable blood-pressure-monitoring devices (e.g., smartphones and smartwatches).

Intensive care photoplethysmogram datasets and machine-learning for blood pressure estimation: Generalization not guarantied

The large MIMIC waveform dataset, sourced from intensive care units, has been used extensively for the development of Photoplethysmography (PPG) based blood pressure (BP) estimation algorithms. Yet, because the data comes from patients in severe conditions-often under the effect of drugs-it is regularly noted that the relationship between BP and PPG signal characteristics may be anomalous, a claim that we investigate here. A sample of 12,000 records from the MIMIC waveform dataset was stacked up against the 219 records of the PPG-BP dataset, an alternative public dataset obtained under controlled experimental conditions. The distribution of systolic and diastolic BP data and 31 PPG pulse morphological features was first compared between datasets. Then, the correlation between features and BP, as well as between the features themselves, was analysed. Finally, regression models were trained for each dataset and validated against the other. Statistical analysis showed significant differences between the datasets in diastolic BP and in 20 out of 31 features when adjusting for heart rate differences. The eight features showing the highest rank correlation to systolic BP in PPG-BP all displayed muted correlation levels in MIMIC. Regression tests showed twice higher baseline predictive power with PPG-BP than with MIMIC. Cross-dataset regression displayed a practically complete loss of predictive power for all models. The differences between the MIMIC and PPG-BP dataset exposed in this study suggest that BP estimation models based on the MIMIC dataset have reduced predictive power on the general population.

A Bayesian method for the automatic extraction of meaningful clinical sequences from large clinical databases

Background: Clinical event recognition can have several applications, such as the examination of clinical stories that can be associated with negative hospital outcomes, or its use in clinical education to assist medical students recognize frequent clinical events. Objective: The purpose of this study is to develop a non-annotated Bayes-based algorithm to extract useful clinical events from medical data. Materials and Methods: We used subsets of MIMIC and CMS LDS datasets that include respiratory diagnoses to calculate two-itemset rules(one item in antecedent and one in consequent) which were used as building blocks for the construction of clinical event sequence order. The main condition for the event sequence is a sequential increase in the conditional probability of two-itemset rules having positive certainty factor, when they are studied together.A clinical event in our framework is defined to be a collection of several blocks of events that meet the aforementioned condition, when considered together. The correctness of our clinical sequences has been validated by two physicians. Results: Our results showed that medical experts scored the rules of this algorithm better than random Apriori rules. A GUI was designed that can be used to examine the association of each clinical event with the clinical outcomes of the length of stay, inpatient mortality, and hospital charges. Conclusion: The present work provides a new approach on how we can improve extraction of clinical event sequences automatically, without user annotation. Our algorithm can successfully find, in several cases, blocks of rules which can tell correct clinical event stories.

Identifying encephalopathy in patients admitted to an intensive care unit: Going beyond structured information using natural language processing.

Encephalopathy is a severe co-morbid condition in critically ill patients that includes different clinical constellation of neurological symptoms. However, even for the most recognised form, delirium, this medical condition is rarely recorded in structured fields of electronic health records precluding large and unbiased retrospective studies. We aimed to identify patients with encephalopathy using a machine learning-based approach over clinical notes in electronic health records. We used a list of ICD-9 codes and clinical concepts related to encephalopathy to define a cohort of patients from the MIMIC-III dataset. Clinical notes were annotated with MedCAT and vectorized with a bag-of-word approach or word embedding using clinical concepts normalised to standard nomenclatures as features. Machine learning algorithms (support vector machines and random forest) trained with clinical notes from patients who had a diagnosis of encephalopathy (defined by ICD-9 codes) were used to classify patients with clinical concepts related to encephalopathy in their clinical notes but without any ICD-9 relevant code. A random selection of 50 patients were reviewed by a clinical expert for model validation. Among 46,520 different patients, 7.5% had encephalopathy related ICD-9 codes in all their admissions (group 1, definite encephalopathy), 45% clinical concepts related to encephalopathy only in their clinical notes (group 2, possible encephalopathy) and 38% did not have encephalopathy related concepts neither in structured nor in clinical notes (group 3, non-encephalopathy). Length of stay, mortality rate or number of co-morbid conditions were higher in groups 1 and 2 compared to group 3. The best model to classify patients from group 2 as patients with encephalopathy (SVM using embeddings) had F1 of 85% and predicted 31% patients from group 2 as having encephalopathy with a probability >90%. Validation on new cases found a precision ranging from 92% to 98% depending on the criteria considered. Natural language processing techniques can leverage relevant clinical information that might help to identify patients with under-recognised clinical disorders such as encephalopathy. In the MIMIC dataset, this approach identifies with high probability thousands of patients that did not have a formal diagnosis in the structured information of the EHR.

Association between predialysis creatinine and mortality in acute kidney injury patients requiring dialysis.

Creatinine is widely used to estimate renal function, but this is not practical in critical illness. Low creatinine has been associated with mortality in many clinical settings. However, the associations between predialysis creatinine level, Sepsis-related Organ Failure Assessment (SOFA) score, fluid overload, and mortality in acute kidney injury patients receiving dialysis therapy (AKI-D) has not been fully addressed. We extracted data for AKI-D patients in the eICU and MIMIC databases. We conducted a retrospective observational cohort study using the eICU dataset. The study cohort was divided into the high-creatine group and the low-creatinine group by the median value (4 mg/dL). The baseline patient information included demographic data, laboratory tests, medications, and comorbid conditions. The independent association of creatinine level with 30-day mortality was examined using multivariate logistic regression analysis. In sensitivity analyses, the associations between creatinine, SOFA score, and mortality were analyzed in patients with or without fluid overload. We also carried out an external validity using the MIMIC dataset. In all 1,600 eICU participants, the 30-day mortality rate was 34.2%. The crude overall mortality rate in the low-creatinine group (44.9%) was significantly higher than that in the high-creatinine group (21.9%; P < 0.001). In the fully adjusted models, the low-creatinine group was associated with a higher risk of 30-day mortality (odds ratio, 1.77; 95% confidence interval, 1.29-2.42; P < 0.001) compared with the high-creatinine group. The low-creatinine group had higher SOFA and nonrenal SOFA scores. In sensitivity analyses, the low-creatinine group had a higher 30-day mortality rate with regard to the BMI or albumin level. Fluid overloaded patients were associated with a significantly worse survival in the low-creatinine group. The results were consistent when assessing the external validity using the MIMIC dataset. In patients with AKI-D, lower predialysis creatinine was associated with increased mortality risk. Moreover, the mortality rate was substantially higher in patients with lower predialysis creatinine with concomitant elevation of fluid overload status.

Transfer learning with DWT based clustering for blood pressure estimation of multiple patients

In this manuscript, we focus on estimating blood pressure (BP) of multiple patients based on easily-collected pulse wave (PW) data efficiently. In detailed, we first design a Convolutional Neural Networks-Gated Recurrent Unit (CNN-GRU) model for BP estimation. Then we propose a transfer learning scheme with Discrete Wavelet Transform (DWT) based k-means clustering algorithm, the so-called TLDK method, to enhance CNN-GRU model for multiple patients. In this method, we employ k-means to cluster the patients based on approximate components of PW data obtained from DWT. Next, a base CNN-GRU model trained on one patient is transferred to other patients within each cluster by freezing parameters of partial layers. As a result, TLDK avoids training models individually for each patient from scratch and improves the generalization ability of models. The numerical results based on MIMIC dataset show that the proposed method is time-saving while achieving superior performance. Therefore, the proposed method can be applied efficiently for convenient BP estimation for multiple patients.

MO360MACHINE LEARNING MODELS FOR PREDICTING ACUTE KIDNEY INJURY: A SYSTEMATIC REVIEW

Abstract Background and Aims Acute kidney injury (AKI) has a substantial impact on global disease burden of Chronic Kidney Disease. To assist physicians with the timely diagnosis of AKI, several prognostic models have been developed to improve early recognition across various patient populations with varying degrees of predictive performance. In the prediction of AKI, machine learning (ML) techniques have been demonstrated to improve on the predictive ability of existing models that rely on more conventional statistical methods. ML is a broad term which refers to various types of models: Parametric models, such as linear or logistic regression use a pre-specified model form which is believed to fit the data, and its parameters are estimated. Non-parametric models, such as decision trees, random forests, and neural networks may have varying complexity (e.g. the depth of a classification tree model) based on the data. Deep learning neural network models exploit temporal or spatial arrangements in the data to deal with complex predictors. Given the rapid growth and development of ML methods and models for AKI prediction over the past years, in this systematic review, we aim to appraise the current state-of-the-art regarding ML models for the prediction of AKI. To this end, we focus on model performance, model development methods, model evaluation, and methodological limitations. Method We searched the PubMed and ArXiv digital libraries, and selected studies that develop or validate an AKI-related multivariable ML prediction model. We extracted data using a data extraction form based on the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) and CHARMS (critical appraisal and data extraction for systematic reviews of prediction modelling studies) checklists. Results Overall, 2,875 titles were screened and thirty-four studies were included. Of those, thirteen studies focussed on intensive care, for which the US derived MIMIC dataset was commonly used; thirty-one studies both developed and validated a model; twenty-one studies used single-centre data. Non-parametric ML methods were used more often than regression and deep learning. Random forests was the most popular method, and often performed best in model comparisons. Deep learning was typically used (and also effective) when complex features were included (e.g., with text or time series). Internal validation was often applied, and the performance of ML models was usually compared against logistic regression. However, the simple training/test split was often used, which does not account for the variability of the training and test samples. Calibration, external validation, and interpretability of results were rarely considered. Comparisons of model performance against medical scores or clinicians were also rare. Reproducibility was limited, as data and code were usually unavailable. Conclusion There is an increasing number of ML models for AKI, which are mostly developed in the intensive care environment largely due to the availability of the MIMIC dataset. Most studies are single-centre, and lack a prospective design. More complex models based on deep learning are emerging, with the potential to improve predictions for complex data, such as time-series, but with the disadvantage of being less interpretable. Future studies should pay attention to using calibration measures, external validation, and on improving model interpretability, in order to improve uptake in clinical practice. Finally, sharing data and code could improve reproducibility of study findings.

TrammelGraph: visual graph abstraction for comparison

Network data, represented by graph-based structures, are used in a variety of applications such as social networks and disease complication networks. A crucial task in many applications is graph comparison, with the goal of understanding the structural differences between pairs of graphs. However, traditional graph visualization techniques, node-link diagrams, and adjacency matrices are not intrinsically designed for comparison tasks. In this paper, we present TrammelGraph, a novel visual graph abstraction technique for graph comparison. TrammelGraph uses graph embedding and node alignment methods to create a map-based representation that eliminates visual clutter and thus facilities graph comparison. The design results in a planar graph with a regularly-spaced, crossing-free layout that helps users identify high-level topological information for graph comparison tasks. To evaluate the effectiveness of TrammelGraph, we conducted a controlled user study with 20 participants that compares TrammelGraph with node-link diagrams and adjacency matrices on a variety of common graph comparison tasks. We also conducted an expert interview with a physician using the MIMIC dataset. Both the quantitative and qualitative results from the study and interview highlighted the key strengths of TrammelGraph as a tool for visual graph comparison.

Mortality prediction model for the triage of COVID-19, pneumonia, and mechanically ventilated ICU patients: A retrospective study

RationalePrediction of patients at risk for mortality can help triage patients and assist in resource allocation. ObjectivesDevelop and evaluate a machine learning-based algorithm which accurately predicts mortality in COVID-19, pneumonia, and mechanically ventilated patients. MethodsRetrospective 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. ResultsWhen 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. ConclusionsThis 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.

Empirical Evaluation of Mimic Software Project Data Sets for Software Effort Estimation

To conduct empirical research on industry software development, it is necessary to obtain data of real software projects from industry. However, only few such industry data sets are publicly available; and unfortunately, most of them are very old. In addition, most of today's software companies cannot make their data open, because software development involves many stakeholders, and thus, its data confidentiality must be strongly preserved. To that end, this study proposes a method for artificially generating a “mimic” software project data set, whose characteristics (such as average, standard deviation and correlation coefficients) are very similar to a given confidential data set. Instead of using the original (confidential) data set, researchers are expected to use the mimic data set to produce similar results as the original data set. The proposed method uses the Box-Muller transform for generating normally distributed random numbers; and exponential transformation and number reordering for data mimicry. To evaluate the efficacy of the proposed method, effort estimation is considered as potential application domain for employing mimic data. Estimation models are built from 8 reference data sets and their concerning mimic data. Our experiments confirmed that models built from mimic data sets show similar effort estimation performance as the models built from original data sets, which indicate the capability of the proposed method in generating representative samples.

Mortality Prediction Model for COVID-19, Pneumonia, and Mechanically Ventilated ICU Patients: A Retrospective Study

Background: The objective of this study was to develop and evaluate a machine learning-based algorithm which accurately predicts mortality in COVID-19, pneumonia, and mechanically ventilated patients. Methods: A retrospective study of 53,001 total ICU patients, including 9,166 patients with pneumonia and 25,895 mechanically ventilated patients, was 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. Findings: W hen trained and tested on the MIMIC dataset, the XGBoost predictor obtained AUROCs of 0.88, 0.86, 0.81, and 0.78 for mortality prediction on mechanically ventilated patients at 12-, 24-, 48-, and 72- hour windows, respectively, and AUROCs of 0.86, 0.82, 0.79, and 0.75 for mortality prediction on pneumonia patients at 12-, 24-, 48-, and 72- hour windows, respectively. The predictor outperformed the qSOFA risk score at all prediction windows. When tested on the community hospital dataset, the predictor obtained AUROCs of 0.934, 0.927, 0.916, and 0.916 for mortality prediction on COVID-19 PCR positive patients at 12-, 24-, 48-, and 72- hour windows, respectively, outperforming the qSOFA risk score at all prediction windows. Interpretation: This machine learning-based algorithm is a useful predictive tool for anticipating patient mortality at clinically useful windows of 12, 24, 48, and 72 hours in advance, and is capable of accurate mortality prediction for mechanically ventilated patients as well as those diagnosed with pneumonia and COVID-19. Trial Registration : This study has been registered on ClinicalTrials.gov under study number NCT 04358510. Funding Statement: N/A Declaration of Interests: All authors who have affiliations listed with Dascena (Oakland, California, USA) are employees or contractors of Dascena. All other authors declare no conflicts of interest Ethics Approval Statement: Studies performed on the de-identified data constitute non-human subject studies, and therefore, our study did not require Institutional Review Board approval.