Development and external validation of deep learning clinical prediction models using variable-length time series data.

OBJECTIVES: To compare and externally validate popular deep learning model architectures and data transformation methods for variable-length time series data in 3 clinical tasks (clinical deterioration, severe acute kidney injury [AKI], and suspected infection). MATERIALS AND METHODS: This multicenter retrospective study included admissions at 2 medical centers that spanned 2007-2022. Distinct datasets were created for each clinical task, with 1 site used for training and the other for testing. Three feature engineering methods (normalization, standardization, and piece-wise linear encoding with decision trees [PLE-DTs]) and 3 architectures (long short-term memory/gated recurrent unit [LSTM/GRU], temporal convolutional network, and time-distributed wrapper with convolutional neural network [TDW-CNN]) were compared in each clinical task. Model discrimination was evaluated using the area under the precision-recall curve (AUPRC) and the area under the receiver operating characteristic curve (AUROC). RESULTS: The study comprised 373 825 admissions for training and 256 128 admissions for testing. LSTM/GRU models tied with TDW-CNN models with both obtaining the highest mean AUPRC in 2 tasks, and LSTM/GRU had the highest mean AUROC across all tasks (deterioration: 0.81, AKI: 0.92, infection: 0.87). PLE-DT with LSTM/GRU achieved the highest AUPRC in all tasks. DISCUSSION: When externally validated in 3 clinical tasks, the LSTM/GRU model architecture with PLE-DT transformed data demonstrated the highest AUPRC in all tasks. Multiple models achieved similar performance when evaluated using AUROC. CONCLUSION: The LSTM architecture performs as well or better than some newer architectures, and PLE-DT may enhance the AUPRC in variable-length time series data for predicting clinical outcomes during external validation.

Predicting neurological outcomes after in-hospital cardiac arrests for patients with Coronavirus Disease 2019.

BACKGROUND: Machine learning models are more accurate than standard tools for predicting neurological outcomes in patients resuscitated after cardiac arrest. However, their accuracy in patients with Coronavirus Disease 2019 (COVID-19) is unknown. Therefore, we compared their performance in a cohort of cardiac arrest patients with COVID-19. METHODS: We conducted a retrospective analysis of resuscitation survivors in the Get With The Guidelines®-Resuscitation (GWTG-R) COVID-19 registry between February 2020 and May 2021. The primary outcome was a favorable neurological outcome, indicated by a discharge Cerebral Performance Category score ≤ 2. Pre- and peri-arrest variables were used as predictors. We applied our published logistic regression, neural network, and gradient boosted machine models developed in patients without COVID-19 to the COVID-19 cohort. We also updated the neural network model using transfer learning. Performance was compared between models and the Cardiac Arrest Survival Post-Resuscitation In-Hospital (CASPRI) score. RESULTS: Among the 4,125 patients with COVID-19 included in the analysis, 484 (12 %) patients survived with favorable neurological outcomes. The gradient boosted machine, trained on non-COVID-19 patients was the best performing model for predicting neurological outcomes in COVID-19 patients, significantly better than the CASPRI score (c-statistic: 0.75 vs 0.67, P < 0.001). While calibration improved for the neural network with transfer learning, it did not surpass the gradient boosted machine in terms of discrimination. CONCLUSION: Our gradient boosted machine model developed in non-COVID patients had high discrimination and adequate calibration in COVID-19 resuscitation survivors and may provide clinicians with important information for these patients.

Identifying infected patients using semi-supervised and transfer learning.

OBJECTIVES: Early identification of infection improves outcomes, but developing models for early identification requires determining infection status with manual chart review, limiting sample size. Therefore, we aimed to compare semi-supervised and transfer learning algorithms with algorithms based solely on manual chart review for identifying infection in hospitalized patients. MATERIALS AND METHODS: This multicenter retrospective study of admissions to 6 hospitals included "gold-standard" labels of infection from manual chart review and "silver-standard" labels from nonchart-reviewed patients using the Sepsis-3 infection criteria based on antibiotic and culture orders. "Gold-standard" labeled admissions were randomly allocated to training (70%) and testing (30%) datasets. Using patient characteristics, vital signs, and laboratory data from the first 24 hours of admission, we derived deep learning and non-deep learning models using transfer learning and semi-supervised methods. Performance was compared in the gold-standard test set using discrimination and calibration metrics. RESULTS: The study comprised 432 965 admissions, of which 2724 underwent chart review. In the test set, deep learning and non-deep learning approaches had similar discrimination (area under the receiver operating characteristic curve of 0.82). Semi-supervised and transfer learning approaches did not improve discrimination over models fit using only silver- or gold-standard data. Transfer learning had the best calibration (unreliability index P value: .997, Brier score: 0.173), followed by self-learning gradient boosted machine (P value: .67, Brier score: 0.170). DISCUSSION: Deep learning and non-deep learning models performed similarly for identifying infection, as did models developed using Sepsis-3 and manual chart review labels. CONCLUSION: In a multicenter study of almost 3000 chart-reviewed patients, semi-supervised and transfer learning models showed similar performance for model discrimination as baseline XGBoost, while transfer learning improved calibration.

Machine learning for phenotyping opioid overdose events.

OBJECTIVE: To develop machine learning models for classifying the severity of opioid overdose events from clinical data. MATERIALS AND METHODS: Opioid overdoses were identified by diagnoses codes from the Marshfield Clinic population and assigned a severity score via chart review to form a gold standard set of labels. Three primary feature sets were constructed from disparate data sources surrounding each event and used to train machine learning models for phenotyping. RESULTS: Random forest and penalized logistic regression models gave the best performance with cross-validated mean areas under the ROC curves (AUCs) for all severity classes of 0.893 and 0.882 respectively. Features derived from a common data model outperformed features collected from disparate data sources for the same cohort of patients (AUCs 0.893 versus 0.837, p value = 0.002). The addition of features extracted from free text to machine learning models also increased AUCs from 0.827 to 0.893 (p value < 0.0001). Key word features extracted using natural language processing (NLP) such as 'Narcan' and 'Endotracheal Tube' are important for classifying overdose event severity. CONCLUSION: Random forest models using features derived from a common data model and free text can be effective for classifying opioid overdose events.

MCIndoor20000: A fully-labeled image dataset to advance indoor objects detection.

A fully-labeled image dataset provides a unique resource for reproducible research inquiries and data analyses in several computational fields, such as computer vision, machine learning and deep learning machine intelligence. With the present contribution, a large-scale fully-labeled image dataset is provided, and made publicly and freely available to the research community. The current dataset entitled MCIndoor20000 includes more than 20,000 digital images from three different indoor object categories, including doors, stairs, and hospital signs. To make a comprehensive dataset addressing current challenges that exist in indoor objects modeling, we cover a multiple set of variations in images, such as rotation, intra-class variation plus various noise models. The current dataset is freely and publicly available at https://github.com/bircatmcri/MCIndoor20000.

Multi-Modal Medical Image Registration with Full or Partial Data: A Manifold Learning Approach.

Multi-modal image registration is the primary step in integrating information stored in two or more images, which are captured using multiple imaging modalities. In addition to intensity variations and structural differences between images, they may have partial or full overlap, which adds an extra hurdle to the success of registration process. In this contribution, we propose a multi-modal to mono-modal transformation method that facilitates direct application of well-founded mono-modal registration methods in order to obtain accurate alignment of multi-modal images in both cases, with complete (full) and incomplete (partial) overlap. The proposed transformation facilitates recovering strong scales, rotations, and translations. We explain the method thoroughly and discuss the choice of parameters. For evaluation purposes, the effectiveness of the proposed method is examined and compared with widely used information theory-based techniques using simulated and clinical human brain images with full data. Using RIRE dataset, mean absolute error of 1.37, 1.00, and 1.41 mm are obtained for registering CT images with PD-, T1-, and T2-MRIs, respectively. In the end, we empirically investigate the efficacy of the proposed transformation in registering multi-modal partially overlapped images.