Exploiting time in electronic health record correlations Hripcsak, George; Albers, David J; Perotte, Adler
Journal of the American Medical Informatics Association : JAMIA,
12/2011, Letnik:
18 Suppl 1, Številka:
Supplement_1
Journal Article
Recenzirano
Odprti dostop
To demonstrate that a large, heterogeneous clinical database can reveal fine temporal patterns in clinical associations; to illustrate several types of associations; and to ascertain the value of ...exploiting time.
Lagged linear correlation was calculated between seven clinical laboratory values and 30 clinical concepts extracted from resident signout notes from a 22-year, 3-million-patient database of electronic health records. Time points were interpolated, and patients were normalized to reduce inter-patient effects.
The method revealed several types of associations with detailed temporal patterns. Definitional associations included low blood potassium preceding 'hypokalemia.' Low potassium preceding the drug spironolactone with high potassium following spironolactone exemplified intentional and physiologic associations, respectively. Counterintuitive results such as the fact that diseases appeared to follow their effects may be due to the workflow of healthcare, in which clinical findings precede the clinician's diagnosis of a disease even though the disease actually preceded the findings. Fully exploiting time by interpolating time points produced less noisy results.
Electronic health records are not direct reflections of the patient state, but rather reflections of the healthcare process and the recording process. With proper techniques and understanding, and with proper incorporation of time, interpretable associations can be derived from a large clinical database.
A large, heterogeneous clinical database can reveal clinical associations, time is an important feature, and care must be taken to interpret the results.
Forecasting blood glucose (BG) levels with routinely collected data is useful for glycemic management. BG dynamics are nonlinear, complex, and nonstationary, which can be represented by nonlinear ...models. However, the sparsity of routinely collected data creates parameter identifiability issues when high-fidelity complex models are used, thereby resulting in inaccurate forecasts. One can use models with reduced physiological fidelity for robust and accurate parameter estimation and forecasting with sparse data. For this purpose, we approximate the nonlinear dynamics of BG regulation by a linear stochastic differential equation: we develop a linear stochastic model, which can be specialized to different settings: type 2 diabetes mellitus (T2DM) and intensive care unit (ICU), with different choices of appropriate model functions. The model includes deterministic terms quantifying glucose removal from the bloodstream through the glycemic regulation system and representing the effect of nutrition and externally delivered insulin. The stochastic term encapsulates the BG oscillations. The model output is in the form of an expected value accompanied by a band around this value. The model parameters are estimated patient-specifically, leading to personalized models. The forecasts consist of values for BG mean and variation, quantifying possible high and low BG levels. Such predictions have potential use for glycemic management as part of control systems. We present experimental results on parameter estimation and forecasting in T2DM and ICU settings. We compare the model's predictive capability with two different nonlinear models built for T2DM and ICU contexts to have a sense of the level of prediction achieved by this model.
Type 2 diabetes mellitus is a complex and under-treated disorder closely intertwined with obesity. Adolescents with severe obesity and type 2 diabetes have a more aggressive disease compared to ...adults, with a rapid decline in pancreatic β cell function and increased incidence of comorbidities. Given the relative paucity of pharmacotherapies, bariatric surgery has become increasingly used as a therapeutic option. However, subsets of this population have sub-optimal outcomes with either inadequate weight loss or little improvement in disease. Predicting which patients will benefit from surgery is a difficult task and detailed physiological characteristics of patients who do not respond to treatment are generally unknown. Identifying physiological predictors of surgical response therefore has the potential to reveal both novel phenotypes of disease as well as therapeutic targets. We leverage data assimilation paired with mechanistic models of glucose metabolism to estimate pre-operative physiological states of bariatric surgery patients, thereby identifying latent phenotypes of impaired glucose metabolism. Specifically, maximal insulin secretion capacity, σ, and insulin sensitivity, S
, differentiate aberrations in glucose metabolism underlying an individual's disease. Using multivariable logistic regression, we combine clinical data with data assimilation to predict post-operative glycemic outcomes at 12 months. Models using data assimilation sans insulin had comparable performance to models using oral glucose tolerance test glucose and insulin. Our best performing models used data assimilation and had an area under the receiver operating characteristic curve of 0.77 (95% confidence interval 0.7665, 0.7734) and mean average precision of 0.6258 (0.6206, 0.6311). We show that data assimilation extracts knowledge from mechanistic models of glucose metabolism to infer future glycemic states from limited clinical data. This method can provide a pathway to predict long-term, post-surgical glycemic states by estimating the contributions of insulin resistance and limitations of insulin secretion to pre-operative glucose metabolism.
Display omitted
•Standard timeseries methods accurately detected physiologic drug effects in EHR data.•Systematic evaluation revealed important interactions of methodological choices.•Indexing ...timeseries by sequence consistently improved drug-effect detection.
We studied how lagged linear regression can be used to detect the physiologic effects of drugs from data in the electronic health record (EHR). We systematically examined the effect of methodological variations ((i) time series construction, (ii) temporal parameterization, (iii) intra-subject normalization, (iv) differencing (lagged rates of change achieved by taking differences between consecutive measurements), (v) explanatory variables, and (vi) regression models) on performance of lagged linear methods in this context. We generated two gold standards (one knowledge-base derived, one expert-curated) for expected pairwise relationships between 7 drugs and 4 labs, and evaluated how the 64 unique combinations of methodological perturbations reproduce the gold standards. Our 28 cohorts included patients in the Columbia University Medical Center/NewYork-Presbyterian Hospital clinical database, and ranged from 2820 to 79,514 patients with between 8 and 209 average time points per patient. The most accurate methods achieved AUROC of 0.794 for knowledge-base derived gold standard (95%CI 0.741, 0.847) and 0.705 for expert-curated gold standard (95% CI 0.629, 0.781). We observed a mean AUROC of 0.633 (95%CI 0.610, 0.657, expert-curated gold standard) across all methods that re-parameterize time according to sequence and use either a joint autoregressive model with time-series differencing or an independent lag model without differencing. The complement of this set of methods achieved a mean AUROC close to 0.5, indicating the importance of these choices. We conclude that time-series analysis of EHR data will likely rely on some of the beneficial pre-processing and modeling methodologies identified, and will certainly benefit from continued careful analysis of methodological perturbations. This study found that methodological variations, such as pre-processing and representations, have a large effect on results, exposing the importance of thoroughly evaluating these components when comparing machine-learning methods.
Display omitted
•Laboratory test measurement patterns provide separate information from test’s values.•Measurement patterns are shaped by the healthcare process and patient health states.•We found 3 ...laboratory measurement patterns: outpatient, inpatient, mixture of both.•Without separating ordering reasons, using lab tests in research can bias results.
Electronic health record (EHR) data show promise for deriving new ways of modeling human disease states. Although EHR researchers often use numerical values of laboratory tests as features in disease models, a great deal of information is contained in the context within which a laboratory test is taken. For example, the same numerical value of a creatinine test has different interpretation for a chronic kidney disease patient and a patient with acute kidney injury. We study whether EHR research studies are subject to biased results and interpretations if laboratory measurements taken in different contexts are not explicitly separated. We show that the context of a laboratory test measurement can often be captured by the way the test is measured through time.
We perform three tasks to study the properties of these temporal measurement patterns. In the first task, we confirm that laboratory test measurement patterns provide additional information to the stand-alone numerical value. The second task identifies three measurement pattern motifs across a set of 70 laboratory tests performed for over 14,000 patients. Of these, one motif exhibits properties that can lead to biased research results. In the third task, we demonstrate the potential for biased results on a specific example. We conduct an association study of lipase test values to acute pancreatitis. We observe a diluted signal when using only a lipase value threshold, whereas the full association is recovered when properly accounting for lipase measurements in different contexts (leveraging the lipase measurement patterns to separate the contexts).
Aggregating EHR data without separating distinct laboratory test measurement patterns can intermix patients with different diseases, leading to the confounding of signals in large-scale EHR analyses. This paper presents a methodology for leveraging measurement frequency to identify and reduce laboratory test biases.
Studies have independently shown associations of lower hemoglobin levels with larger admission intracerebral hemorrhage (ICH) volumes and worse outcomes. We investigated whether lower admission ...hemoglobin levels are associated with more hematoma expansion (HE) after ICH and whether this mediates lower hemoglobin levels' association with worse outcomes.
Consecutive patients enrolled between 2009 and 2016 to a single-center prospective ICH cohort study with admission hemoglobin and neuroimaging data to calculate HE (>33% or >6 mL) were evaluated. The association of admission hemoglobin levels with HE and poor clinical outcomes using modified Rankin Scale (mRS 4-6) were assessed using separate multivariable logistic regression models. Mediation analysis investigated causal associations among hemoglobin, HE, and outcome.
Of 256 patients with ICH meeting inclusion criteria, 63 (25%) had HE. Lower hemoglobin levels were associated with increased odds of HE (odds ratio OR 0.80 per 1.0 g/dL change of hemoglobin; 95% confidence interval CI 0.67-0.97) after adjusting for previously identified covariates of HE (admission hematoma volume, antithrombotic medication use, symptom onset to admission CT time) and hemoglobin (age, sex). Lower hemoglobin was also associated with worse 3-month outcomes (OR 0.76 per 1.0 g/dL change of hemoglobin; 95% CI 0.62-0.94) after adjusting for ICH score. Mediation analysis revealed that associations of lower hemoglobin with poor outcomes were mediated by HE (
= 0.01).
Further work is required to replicate the associations of lower admission hemoglobin levels with increased odds of HE mediating worse outcomes after ICH. If confirmed, an investigation into whether hemoglobin levels can be a modifiable target of treatment to improve ICH outcomes may be warranted.
Ventilator dyssynchrony (VD) can worsen lung injury and is challenging to detect and quantify due to the complex variability in the dyssynchronous breaths. While machine learning (ML) approaches are ...useful for automating VD detection from the ventilator waveform data, scalable severity quantification and its association with pathogenesis and ventilator mechanics remain challenging.
We develop a systematic framework to quantify pathophysiological features observed in ventilator waveform signals such that they can be used to create feature-based severity stratification of VD breaths.
A mathematical model was developed to represent the pressure and volume waveforms of individual breaths in a feature-based parametric form. Model estimates of respiratory effort strength were used to assess the severity of flow-limited (FL)-VD breaths compared to normal breaths. A total of 93,007 breath waveforms from 13 patients were analyzed.
A novel model-defined continuous severity marker was developed and used to estimate breath phenotypes of FL-VD breaths. The phenotypes had a predictive accuracy of over 97% with respect to the previously developed ML-VD identification algorithm. To understand the incidence of FL-VD breaths and their association with the patient state, these phenotypes were further successfully correlated with ventilator-measured parameters and electronic health records.
This work provides a computational pipeline to identify and quantify the severity of FL-VD breaths and paves the way for a large-scale study of VD causes and effects. This approach has direct application to clinical practice and in meaningful knowledge extraction from the ventilator waveform data.
Display omitted
•Ventilator dyssynchrony may instigate and exacerbate ventilator-induced lung injury.•Identifying and quantifying patient-ventilator dyssynchrony is necessary.•Quantifiable breath phenotypes of flow-limited dyssynchronous breaths are created.•An efficient pipeline is developed to extract knowledge from the waveform data.