Search

Background: Patients' choices of providers when undergoing elective surgeries significantly impact both perioperative outcomes and costs. There exist a variety of approaches that are available to patients for evaluating between different hospital choices.Objective: This paper aims to compare differences in outcomes and costs between hospitals ranked using popular internet-based consumer ratings, quality stars, reputation rankings, average volumes, average outcomes, and precision machine learning-based rankings for hospital settings performing hip replacements in a large metropolitan area.Methods: Retrospective data from 4192 hip replacement surgeries among Medicare beneficiaries in 2018 in a the Chicago metropolitan area were analyzed for variations in outcomes (90-day postprocedure hospitalizations and emergency department visits) and costs (90-day total cost of care) between hospitals ranked through multiple approaches: internet-based consumer ratings, quality stars, reputation rankings, average yearly surgical volume, average outcome rates, and machine learning-based rankings. The average rates of outcomes and costs were compared between the patients who underwent surgery at a hospital using each ranking approach in unadjusted and propensity-based adjusted comparisons.Results: Only a minority of patients (1159/4192, 27.6% to 2078/4192, 49.6%) were found to be matched to higher-ranked hospitals for each of the different approaches. Of the approaches considered, hip replacements at hospitals that were more highly ranked by consumer ratings, quality stars, and machine learning were all consistently associated with improvements in outcomes and costs in both adjusted and unadjusted analyses. The improvement was greatest across all metrics and analyses for machine learning-based rankings.Conclusions: There may be a substantive opportunity to increase the number of patients matched to appropriate hospitals across a broad variety of ranking approaches. Elective hip replacement surgeries performed at hospitals where patients were matched based on patient-specific machine learning were associated with better outcomes and lower total costs of care. [ABSTRACT FROM AUTHOR]

Quantifying hemodynamic severity in patients with heart failure (HF) is an integral part of clinical care. A key indicator of hemodynamic severity is the mean Pulmonary Capillary Wedge Pressure (mPCWP), which is ideally measured invasively. Accurate non-invasive estimates of the mPCWP in patients with heart failure would help identify individuals at the greatest risk of a HF exacerbation. We developed a deep learning model, HFNet, that uses the 12-lead electrocardiogram (ECG) together with age and sex to identify when the mPCWP > 18 mmHg in patients who have a prior diagnosis of HF. The model was developed using retrospective data from the Massachusetts General Hospital and evaluated on both an internal test set and an independent external validation set, from another institution. We developed an uncertainty score that identifies when model performance is likely to be poor, thereby helping clinicians gauge when to trust a given model prediction. HFNet AUROC for the task of estimating mPCWP > 18 mmHg was 0.8 2 ± 0.01 and 0. 81 ± 0.01 on the internal and external datasets, respectively. The AUROC on predictions with the highest uncertainty are 0.50 ± 0.02 (internal) and 0. 56 ± 0.04 (external), while the AUROC on predictions with the lowest uncertainty were 0.86 ± 0.01 (internal) and 0.82 ± 0.01 (external). Using estimates of the prevalence of mPCWP > 18 mmHg in patients with reduced ventricular function, and a decision threshold corresponding to an 80% sensitivity, the calculated positive predictive value (PPV) is 0. 89 ± 0.01when the corresponding chest x-ray (CXR) is consistent with interstitial edema HF. When the CXR is not consistent with interstitial edema, the estimated PPV is 0. 78 ± 0.02, again at an 80% sensitivity threshold. HFNet can accurately predict elevated mPCWP in patients with HF using the 12-lead ECG and age/sex. The method also identifies cohorts in which the model is more/less likely to produce accurate outputs. [ABSTRACT FROM AUTHOR]

In this paper, we present an automated approach to discover patterns that can distinguish between sequences belonging to different labeled groups. Our method searches for approximately conserved motifs that occur with varying statistical properties in positive and negative training examples. We propose a two-step process to discover such patterns. Using locality sensitive hashing (LSH), we first estimate the frequency of all subsequences and their approximate matches within a given Hamming radius in labeled examples. The discriminative ability of each pattern is then assessed from the estimated frequencies by concordance and rank sum testing. The use of LSH to identify approximate matches for each candidate pattern helps reduce the runtime of our method. Space requirements are reduced by decomposing the search problem into an iterative method that uses a single LSH table in memory. We propose two further optimizations to the search for discriminative patterns. Clustering with redundancy based on a 2-approximate solution of the k-center problem decreases the number of overlapping approximate groups while providing exhaustive coverage of the search space. Sequential statistical methods allow the search process to use data from only as many training examples as are needed to assess significance. We evaluated our algorithm on data sets from different applications to discover sequential patterns for classification. On nucleotide sequences from the Drosophila genome compared with random background sequences, our method was able to discover approximate binding sites that were preserved upstream of genes. We observed a similar result in experiments on ChIP-on-chip data. For cardiovascular data from patients admitted with acute coronary syndromes, our pattern discovery approach identified approximately conserved sequences of morphology variations that were predictive of future death in a test population. Our data showed that the use of LSH, clustering, and sequential statistics improved the running time of the search algorithm by an order of magnitude without any noticeable effect on accuracy. These results suggest that our methods may allow for an unsupervised approach to efficiently learn interesting dissimilarities between positive and negative examples that may have a functional role. [ABSTRACT FROM AUTHOR]

Importance: When hospitals are at capacity, accurate deterioration indices could help identify low-risk patients as potential candidates for home care programs and alleviate hospital strain. To date, many existing deterioration indices are based entirely on structured data from the electronic health record (EHR) and ignore potentially useful information from other sources. Objective: To improve the accuracy of existing deterioration indices by incorporating unstructured imaging data from chest radiographs. Design, setting, and participants: Machine learning models were trained to predict deterioration of patients hospitalized with acute dyspnea using existing deterioration index scores and chest radiographs. Models were trained on hospitalized patients without coronavirus disease 2019 (COVID-19) and then subsequently tested on patients with COVID-19 between January 2020 and December 2020 at a single tertiary care center who had at least one radiograph taken within 48 hours of hospital admission. Main outcomes and measures: Patient deterioration was defined as the need for invasive or non-invasive mechanical ventilation, heated high flow nasal cannula, IV vasopressor administration or in-hospital mortality at any time following admission. The EPIC deterioration index was augmented with unstructured data from chest radiographs to predict risk of deterioration. We compared discriminative performance of the models with and without incorporating chest radiographs using area under the receiver operating curve (AUROC), focusing on comparing the fraction and total patients identified as low risk at different negative predictive values (NPV). Results: Data from 6278 hospitalizations were analyzed, including 5562 hospitalizations without COVID-19 (training cohort) and 716 with COVID-19 (216 in validation, 500 in held-out test cohort). At a NPV of 0.95, the best-performing image-augmented deterioration index identified 49 more (9.8%) individuals as low-risk compared to the deterioration index based on clinical data alone in the first 48 hours of admission. At a NPV of 0.9, the EPIC image-augmented deterioration index identified 26 more individuals (5.2%) as low-risk compared to the deterioration index based on clinical data alone in the first 48 hours of admission. Conclusion and relevance: Augmenting existing deterioration indices with chest radiographs results in better identification of low-risk patients. The model augmentation strategy could be used in the future to incorporate other forms of unstructured data into existing disease models. [ABSTRACT FROM AUTHOR]

This study investigates acoustic voice and speech features as biomarkers for acute decompensated heart failure (ADHF), a serious escalation of heart failure symptoms including breathlessness and fatigue. ADHF-related systemic fluid accumulation in the lungs and laryngeal tissues is hypothesized to affect phonation and respiration for speech. A set of daily spoken recordings from 52 patients undergoing inpatient ADHF treatment was analyzed to identify voice and speech biomarkers for ADHF and to examine the trajectory of biomarkers during treatment. Results indicated that speakers produce more stable phonation, a more creaky voice, faster speech rates, and longer phrases after ADHF treatment compared to their pre-treatment voices. This project builds on work to develop a method of monitoring ADHF using speech biomarkers and presents a more detailed understanding of relevant voice and speech features., Competing Interests: Robert E. Hillman and Daryush D. Mehta have a financial interest in InnoVoyce LLC, a company focused on developing and commercializing technologies for the prevention, diagnosis, and treatment of voice-related disorders. Hillman’s and Mehta’s interests were reviewed and are managed by Massachusetts General Hospital and Mass General Brigham in accordance with their conflict-of-interest policies. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.

Objective: To use echocardiographic and clinical features to develop an explainable clinical risk prediction model in patients with aortic stenosis (AS), including those with low-gradient AS (LGAS), using machine learning (ML)., Methods: In 1130 patients with moderate or severe AS, we used bootstrap lasso regression (BLR), an ML method, to identify echocardiographic and clinical features important for predicting the combined outcome of all-cause mortality or aortic valve replacement (AVR) within 5 years after the initial echocardiogram. A separate hold out set, from a different centre (n=540), was used to test the generality of the model. We also evaluated model performance with respect to each outcome separately and in different subgroups, including patients with LGAS., Results: Out of 69 available variables, 26 features were identified as predictive by BLR and expert knowledge was used to further reduce this set to 9 easily available and input features without loss of efficacy. A ridge logistic regression model constructed using these features had an area under the receiver operating characteristic curve (AUC) of 0.74 for the combined outcome of mortality/AVR. The model reliably identified patients at high risk of death in years 2-5 (HRs ≥2.0, upper vs other quartiles, for years 2-5, p<0.05, p=not significant in year 1) and was also predictive in the cohort with LGAS (n=383, HRs≥3.3, p<0.05). The model performed similarly well in the independent hold out set (AUC 0.78, HR ≥2.5 in years 1-5, p<0.05)., Conclusion: In two separate longitudinal databases, ML identified prognostic features and produced an algorithm that predicts outcome for up to 5 years of follow-up in patients with AS, including patients with LGAS. Our algorithm, the Aortic Stenosis Risk (ASteRisk) score, is available online for public use., Competing Interests: Competing interests: PP has received funding from Edwards Lifesciences and Medtronic for echocardiography core lab or in vitro analyses with no personal compensation., (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY. Published by BMJ.)

We introduce HyperMorph, a framework that facilitates efficient hyperparameter tuning in learning-based deformable image registration. Classical registration algorithms perform an iterative pair-wise optimization to compute a deformation field that aligns two images. Recent learning-based approaches leverage large image datasets to learn a function that rapidly estimates a deformation for a given image pair. In both strategies, the accuracy of the resulting spatial correspondences is strongly influenced by the choice of certain hyperparameter values. However, an effective hyperparameter search consumes substantial time and human effort as it often involves training multiple models for different fixed hyperparameter values and may lead to suboptimal registration. We propose an amortized hyperparameter learning strategy to alleviate this burden by learning the impact of hyperparameters on deformation fields. We design a meta network, or hypernetwork, that predicts the parameters of a registration network for input hyperparameters, thereby comprising a single model that generates the optimal deformation field corresponding to given hyperparameter values. This strategy enables fast, high-resolution hyperparameter search at test-time, reducing the inefficiency of traditional approaches while increasing flexibility. We also demonstrate additional benefits of HyperMorph, including enhanced robustness to model initialization and the ability to rapidly identify optimal hyperparameter values specific to a dataset, image contrast, task, or even anatomical region, all without the need to retrain models. We make our code publicly available at http://hypermorph.voxelmorph.net., Competing Interests: Conflicts of Interest Bruce Fischl has a financial interest in CorticoMetrics, and his interests are reviewed and managed by Massachusetts General Hospital and Mass General Brigham in accordance with their conflict of interest policies.

Artificial intelligence (AI) models for decision support have been developed for clinical settings such as radiology, but little work evaluates the potential impact of such systems. In this study, physicians received chest X-rays and diagnostic advice, some of which was inaccurate, and were asked to evaluate advice quality and make diagnoses. All advice was generated by human experts, but some was labeled as coming from an AI system. As a group, radiologists rated advice as lower quality when it appeared to come from an AI system; physicians with less task-expertise did not. Diagnostic accuracy was significantly worse when participants received inaccurate advice, regardless of the purported source. This work raises important considerations for how advice, AI and non-AI, should be deployed in clinical environments.

Objectives: To evaluate the utility of machine learning (ML) for the management of Medicare beneficiaries at risk of severe respiratory infections in community and postacute settings by (1) identifying individuals in a community setting at risk of infections resulting in emergent hospitalization and (2) matching individuals in a postacute setting to skilled nursing facilities (SNFs) that are likely to reduce the risk of infections., Study Design: Retrospective analysis of claims from 2 million Medicare beneficiaries for 2017-2019., Methods: In the first analysis, the rate of emergent hospitalization due to respiratory infections was measured among beneficiaries predicted by ML to be at highest risk and compared with the overall average for the population. In the second analysis, the rate of emergent hospitalization due to respiratory infections was compared between beneficiaries who went to an SNF with lower predicted risk of infections using ML and beneficiaries who did not., Results: In the community setting, beneficiaries predicted to be at highest risk had significantly increased rates of emergency department visits (13-fold) and hospitalizations (18-fold) due to respiratory infections. In the postacute setting, beneficiaries who received care at top-recommended SNFs had a relative reduction of 37% for emergent care and 36% for inpatient hospitalization due to respiratory infection., Conclusions: Precision management through personalized and predictive ML offers the opportunity to reduce the burden of outbreaks of respiratory infections. In the community setting, ML can identify vulnerable subpopulations at highest risk of severe infections. In postacute settings, ML can inform patient choices by matching beneficiaries to SNFs likely to reduce future risk.

Recently, researchers have started training high complexity machine learning models to clinical tasks, often improving upon previous benchmarks. However, more often than not, these methods require large amounts of supervision to provide good generalization guarantees. When applied to data coming from small cohorts and long monitoring periods these models are prone to overfit to subject-identifying features. Since obtaining large amounts of labels is usually not practical in many scenarios, expert-driven knowledge of the task is a common technique to prevent overfitting. We present a two-step learning approach that is able to generalize under these circumstances when applied to a voice monitoring dataset. Our approach decouples the feature learning stage and performs it in an unsupervised manner, removing the need for laborious feature engineering. We show the effectiveness of our proposed model on two voice monitoring related tasks. We evaluate the extracted features for classifying between patients with vocal fold nodules and controls. We also demonstrate that the features capture pathology relevant information by showing that models trained on them are more accurate predicting vocal use for patients than for controls. Our proposed method is able to generalize to unseen subjects and across learning tasks while matching state-of-the-art results.

OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH). METHODS We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital. RESULTS Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80-0.84) and 0.75 ( 95% CI, 0.73-0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities. CONCLUSION A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies. Infect Control Hosp Epidemiol 2018;39:425-433.

Voice disorders affect an estimated 14 million working-aged Americans, and many more worldwide. We present the first large scale study of vocal misuse based on long-term ambulatory data collected by an accelerometer placed on the neck. We investigate an unsupervised data mining approach to uncovering latent information about voice misuse. We segment signals from over 253 days of data from 22 subjects into over a hundred million single glottal pulses (closures of the vocal folds), cluster segments into symbols, and use symbolic mismatch to uncover differences between patients and matched controls, and between patients pre- and post-treatment. Our results show significant behavioral differences between patients and controls, as well as between some pre- and post-treatment patients. Our proposed approach provides an objective basis for helping diagnose behavioral voice disorders, and is a first step towards a more data-driven understanding of the impact of voice therapy.

Classification tree-based risk stratification models generate easily interpretable classification rules. This feature makes classification tree-based models appealing for use in a clinical setting, provided that they have comparable accuracy to other methods. In this paper, we present and evaluate the performance of a non-symmetric entropy-based classification tree algorithm. The algorithm is designed to accommodate class imbalance found in many medical datasets. We evaluate the performance of this algorithm, and compare it to that of SVM-based classifiers, when applied to 4219 non-ST elevation acute coronary syndrome patients. We generated SVM-based classifiers using three different strategies for handling class imbalance: cost-sensitive SVM learning, synthetic minority oversampling (SMOTE), and random majority undersampling. We used both linear and radial basis kernel-based SVMs. Our classification tree models outperformed SVM-based classifiers generated using each of the three techniques. On average, the classification tree models yielded a 14% improvement in G-score and a 21% improvement in F-score relative to the linear SVM classifiers with the best performance. Similarly, our classification tree models yielded a 12% improvement in G-score and a 21% improvement in the F-score over the best RBF kernel-based SVM classifiers.

Little effort has been devoted to developing algorithms that can detect the cessation of seizure activity in scalp EEG. Such algorithms could facilitate clinical applications such as the estimation of seizure duration or the delivery of therapies designed to mitigate postictal period symptoms. In this paper, we present a method for detecting the termination of seizure activity. When tested on 133 seizures from a public database, our method detected the end of 132 seizures with a mean absolute error of 10.3 ± 5.5 seconds of the time marked by an electroencephalographer. Furthermore, by pairing our seizure end detector with a previously published seizure onset detector, we could automatically estimate the duration of 85% of test seizures within a 15 second error margin.

We present an adaptive binary classification algorithm, based on transductive transfer learning. We illustrate the method in the context of electrocardiogram (ECG) analysis. Knowledge gained from a population of patients is automatically adapted to patients' records to accurately detect ectopic beats. On patients from the MIT-BIH Arrhythmia Database, we achieve a median sensitivity of 94.59% and positive predictive value of 96.24%, for the binary classification task of separating premature ventricular contractions (PVCs), a type of ectopic beat, from non-PVCs.

We present an approach to identifying and reconstructing corrupted regions in a multi-parameter physiological signal. The method, which uses information in correlated signals, is specifically designed to preserve clinically significant aspects of the signals. We use template matching to jointly segment the multi-parameter signal, morphological dissimilarity to estimate the quality of the signal segment, similarity search using features on a database of templates to find the closest match, and time-warping to reconstruct the corrupted segment with the matching template. In experiments carried out on the MIT-BIH Arrhythmia Database, a two-parameter database with many clinically significant arrhythmias, our method improved the classification accuracy of the beat type by more than 7 times on a signal corrupted with white Gaussian noise, and increased the similarity to the original signal, as measured by the normalized residual distance, by more than 2.5 times.

Telemedicine has had a positive impact on some aspects of patient care. However, existing telemedicine systems that use high-quality video are inflexible, requiring investment in fixed infrastructure. We have overcome a number of technical challenges to build a mobile telemedicine system that can reliably deliver high-quality video from both stationary sites and moving vehicles. Our system is constructed using custom software and off-the-shelf hardware, and opportunistically aggregates wireless data connections from different providers. We have evaluated the communication capabilities of our system in a number of realistic experiments. We are about to launch an evaluation of the clinical utility of our system. The system will be used to allow neonatal specialists to participate in the care of critically ill infants at remote sites and during transport.

During an ongoing study of wireless vital signs monitoring of post-triage patients with SMART [1] in the waiting area of the emergency department (ED) at the Brigham and Women's Hospital in Boston, Massachusetts, USA, we observed that redundancy in vital signs monitoring can be advantageous.

In this paper we quantify the degree to which patient-specificity affects the detection latency, sensitivity, and specificity of a seizure detector using 536 hours of continuously recorded scalp EEG from 16 epilepsy patients. We demonstrate that a detector that knows of an individual's seizure and non-seizure EEG outperforms a detector limited to knowledge of an individual's non-seizure EEG, and a detector limited to knowledge of population seizure and non-seizure EEG.

We are building an ambulatory version of a patient-specific epileptic seizure detector based on scalp EEG signals. Since patients have to wear the electrodes all the time, it is desirable to use the minimum number of electrodes needed to achieve good performance. In this paper, we describe a method that uses recursive feature elimination (RFE) to design detectors that use small numbers of electrodes. We also present results that indicate that the appropriate number of electrodes varies across patients. It is frequently the case that a surprisingly small number of electrodes, sometimes as few as two, suffices to construct a detector with expected performance comparable to that of detectors that use a full twenty-one-channel montage.

Listening to heart sounds during physical exams can offer useful clues to the presence of cardiac disease. Cardiac auscultation is non-invasive, inexpensive and fast. It is also highly unreliable, and requires good hearing and considerable expertise. In this paper, we describe an audio-visual tool designed to help people learn to be better at cardiac auscultation. The use of digital signal processing techniques makes pathological findings more recognizable in both audio and visual representations. This reduces dependence on the ability of people to hear relevant information.

This paper describes an approach to building a high-quality mobile telemedicine system that overcomes the limitations of individual public wireless data networks. Public wireless data channels do not have the capacity to handle the high-bandwidth video needed for applications such as remote evaluation of trauma and stroke patients. Network striping allows us to aggregate multiple physical channels to meet the bandwidth requirements for the video. We have developed flexible network-striping software middleware, and are building a telemedicine system using that middleware. Our approach uses existing communications infrastructure and conventional-off-the-shelf components, making the system easy to deploy.

Ambulatory EEG recorders are commercially available. The majority of these recorders are only capable of capturing and storing EEG for later review by clinicians. A few models are equipped with real-time seizure event detectors, but these detectors make no guarantees on when during a seizure a detection is made. This renders current ambulatory EEG recorders unsuitable for activating alarms or initiating therapies to acutely impact seizure progression in the ambulatory setting. Integrating seizure onset detectors into existing ambulatory recorders will make these applications feasible. Successful integration requires that these detectors be executable on the resource-limited digital signal processors found within ambulatory recorders. In this paper we describe the integration of a patient-specific seizure onset detector with a commercially available ambulatory EEG recorder, and demonstrate how such integration could enable the detection of seizure onset in the ambulatory setting.

This paper presents an automated, patient-specific method for the detection of epileptic seizure onsets from noninvasive EEG. We adopt a patient-specific approach to exploit the consistency of an individual patient's seizure and non-seizure EEG. Our method uses a wavelet decomposition to construct a feature vector that captures the morphology and spatial distribution of an EEG epoch, and then determines whether that vector is representative of a patient's seizure or non-seizure EEG using the support-vector machine classification algorithm. Our completely automated method was tested on non-invasive EEG from thirty-six pediatric subjects suffering from a variety of seizure types. It detected 131 of 139 seizure events within 8.0+/-3.2 seconds following electrographic onset, and declared 15 false-detections in 60 hours of clinical EEG. Our patient-specific method can be used to initiate delay-sensitive clinical procedures following seizure onset; for example, the injection of an imaging radiopharmaceutical or stimulation of the vagus nerve.