Using automated clinical data for risk adjustment: development and validation of six disease-specific mortality predictive models for pay-for-performance

BACKGROUND: Clinically plausible risk-adjustment methods are needed to implement pay-for-performance protocols. Because billing data lacks clinical precision, may be gamed, and chart abstraction is costly, we sought to develop predictive models for mortality that maximally used automated laboratory data and intentionally minimized the use of administrative data (Laboratory Models). We also evaluated the additional value of vital signs and altered mental status (Full Models). METHODS: Six models predicting in-hospital mortality for ischemic and hemorrhagic stroke, pneumonia, myocardial infarction, heart failure, and septicemia were derived from 194,903 admissions in 2000-2003 across 71 hospitals that imported laboratory data. Demographics, admission-based labs, International Classification of Diseases (ICD)-9 variables, vital signs, and altered mental status were sequentially entered as covariates. Models were validated using abstractions (629,490 admissions) from 195 hospitals. Finally, we constructed hierarchical models to compare hospital performance using the Laboratory Models and the Full Models. RESULTS: Model c-statistics ranged from 0.81 to 0.89. As constructed, laboratory findings contributed more to the prediction of death compared with any other risk factor characteristic groups across most models except for stroke, where altered mental status was more important. Laboratory variables were between 2 and 67 times more important in predicting mortality than ICD-9 variables. The hospital-level risk-standardized mortality rates derived from the Laboratory Models were highly correlated with the results derived from the Full Models (average rho = 0.92). CONCLUSIONS: Mortality can be well predicted using models that maximize reliance on objective pathophysiologic variables whereas minimizing input from billing data. Such models should be less susceptible to the vagaries of billing information and inexpensive to implement.     

HoloPhaseNet: fully automated deep-learning-based hologram reconstruction using a conditional generative adversarial model

Quantitative phase imaging with off-axis digital holography in a microscopic configuration provides insight into the cells’ intracellular content and morphology. This imaging is conventionally achieved by numerical reconstruction of the recorded hologram, which requires the precise setting of the reconstruction parameters, including reconstruction distance, a proper phase unwrapping algorithm, and component of wave vectors. This paper shows that deep learning can perform the complex light propagation task independent of the reconstruction parameters. We also show that the super-imposed twin-image elimination technique is not required to retrieve the quantitative phase image. The hologram at the single-cell level is fed into a trained image generator (part of a conditional generative adversarial network model), which produces the phase image. Also, the model’s generalization is demonstrated by training it with holograms of size 512×512 pixels, and the resulting quantitative analysis is shown.     

循证临床药学实践——概念、实践模式及步骤

循证医学(evidence-based medicine,EBM)自20世纪90年代产生以来,其理念、方法已逐步渗透到医药卫生和决策与管理的各个领域,循证内科学、循证外科学、循证公共卫生、循证决策等相继出现,循证药学(Evidence-based pharmacy)、循证     

Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation

Registration is a core component of many imaging pipelines. In case of clinical scans, with lower resolution and sometimes substantial motion artifacts, registration can produce poor results. Visual assessment of registration quality in large clinical datasets is inefficient. In this work, we propose to automatically assess the quality of registration to an atlas in clinical FLAIR MRI scans of the brain. The method consists of automatically segmenting the ventricles of a given scan using a neural network, and comparing the segmentation to the atlas ventricles propagated to image space. We used the proposed method to improve clinical image registration to a general atlas by computing multiple registrations - one directly to the general atlas and others via different age-specific atlases - and then selecting the registration that yielded the highest ventricle overlap. Finally, as an example application of the complete pipeline, a voxelwise map of white matter hyperintensity burden was computed using only the scans with registration quality above a predefined threshold. Methods were evaluated in a single-site dataset of more than 1000 scans, as well as a multi-center dataset comprising 142 clinical scans from 12 sites. The automated ventricle segmentation reached a Dice coefficient with manual annotations of 0.89 in the single-site dataset, and 0.83 in the multi-center dataset. Registration via age-specific atlases could improve ventricle overlap compared to a direct registration to the general atlas (Dice similarity coefficient increase up to 0.15). Experiments also showed that selecting scans with the registration quality assessment method could improve the quality of average maps of white matter hyperintensity burden, instead of using all scans for the computation of the white matter hyperintensity map. In this work, we demonstrated the utility of an automated tool for assessing image registration quality in clinical scans. This image quality assessment step could ultimately assist in the translation of automated neuroimaging pipelines to the clinic.     

Predictive modeling of total healthcare costs using pharmacy claims data: a comparison of alternative econometric cost modeling techniques

OBJECTIVE: We sought to evaluate several statistical modeling approaches in predicting prospective total annual health costs (medical plus pharmacy) of health plan participants using Pharmacy Health Dimensions (PHD), a pharmacy claims-based risk index. METHODS: We undertook a 2-year (baseline year/follow-up year) longitudinal analysis of integrated medical and pharmacy claims. Included were plan participants younger than 65 years of age with continuous medical and pharmacy coverage (n = 344,832). PHD drug categories, age, gender, and pharmacy costs were derived across the baseline year. Annual total health costs were calculated for each plan participant in follow-up year. Models examined included ordinary least squares (OLS) regression, log-transformed OLS regression with smearing estimator, and 3 two-part models using OLS regression, log-OLS regression with smearing estimator, and generalized linear modeling (GLM), respectively. A 10% random sample was withheld for model validation, which was assessed via adjusted r, mean absolute prediction error, specificity, and positive predictive value. RESULTS: Most PHD drug categories were significant independent predictors of total costs. Among models tested, the OLS model had the lowest mean absolute prediction error and highest adjusted r. The log-OLS and 2-part log-OLS models did not predict costs accurately as the result of issues of log-scale heteroscedasticity. The 2-part model using GLM had lower adjusted r but similar performance in other assessment measures compared with the OLS or 2-part OLS models. CONCLUSION: The PHD system derived solely from pharmacy claims data can be used to predict future total health costs. Using PHD with a simple OLS model may provide similar predictive accuracy in comparison to more advanced econometric models.     

Development of an automated individual tree detection model using point cloud LiDAR data for accurate tree counts in a Pinus radiata plantation

We develop and evaluate a new individual tree detection (ITD) algorithm to automatically locate and estimate the number of individual trees within a Pinus radiata plantation from relatively sparse airborne LiDAR point cloud data. The area of interest comprised stands covering a range of age classes and stocking levels. Our approach is based on local maxima (LM) filtering that tackles the issue of selecting the optimal search radius from the LiDAR point cloud for every potential LM using metrics derived from local neighbourhood data points; thus, it adapts to the local conditions, irrespective of canopy variability. This was achieved through two steps: (i) logistic regression model development using simulated stands composed of individual trees derived from real LiDAR point cloud data and (ii) application testing of the model using real plantation LiDAR point cloud data and geolocated, tree-level reference crowns that were manually identified in the LiDAR imagery. Our ITD algorithm performed well compared with previous studies, producing RMSE of 5.7% and a bias of only ?2.4%. Finally, we suggest that the ITD algorithm can be used for accurately estimating stocking and tree mapping, which in turn could be used to derive the plot-level metrics for an area-based approach for enhancing estimates of stand-level inventory attributes based on plot imputation.     

Estimation of left ventricular compliance using on-line echocardiographic automated border detection and pressure data

The end-diastolic pressure-volume relationship can be used to describe left ventricular (LV) compliance. The objective of this study was to utilize measurements of LV cavity area by echocardiographic automated border detection and pressure data to estimate the end-diastolic pressure-volume curve in an isolated heart preparation where true volume could be measured by an intraventricular balloon. Six dog hearts were excised for placement of an intraventricular balloon and a micromanometer catheter and perfused in anex vivo circuit. Mid-ventricular short-axis images were used to measure cross-sectional area by automated border detection while LV volumes were increased from 5 ml to maximal volume (30–40 ml) in each preparation. Simultaneous area and pressure data were recorded on a computer workstation through a customized interface with the ultrasound system. Three runs of varying LV volumes at 1 ml increments were performed on each of 6 hearts for a total of 1,080 simultaneous measurements. Pressure-volume and pressure-area curves were analyzed by linear regression analyses, the slope of which was used to estimate compliance. End-diastolic pressure-area and pressure-volume relationships were significantly correlated with mean r=0.97 ± 0.02 (p<0.001) from individual hearts. The slopes which served to estimate compliance of the individual pressure-area and pressure-volume curves were similar and differed by only 7±4%. A similar correlation was observed by second order regression analyses with r=0.97±0.01 (p<0.001) for pressure-area and r=0.98±0.01 (p<0.001) for pressure-volume relationships. The end-diastolic pressure-area curves may potentially be used to estimate LV compliance, although the clinical application of this method remains to be validated.     

Estimating risk factors for patients with potential drug-related problems using electronic pharmacy data. IMPROVE investigators.

OBJECTIVE: To validate a computer-based program to identify patients at high risk for drug-related problems. DESIGN: Computerized analysis of pharmacy dispensing records and manual review of medical records. SETTING: Ambulatory clinics at a Veterans Affairs Medical Center. PATIENTS: 246 randomly selected patients who were receiving at least one outpatient medication in the previous 24 months. MAIN OUTCOME MEASURES: Presence of six previously established criteria regarding medication use. These criteria are five or more medications, > or = 12 doses per day, four or more changes to the medication regimen, three or more chronic diseases, history of noncompliance, and presence of a drug requiring therapeutic drug monitoring (TDM). RESULTS: Spearman rho rank order correlation coefficients ranged from 0.63 to 0.91 for criteria pertaining to the number of medications, daily doses, changes in the medication regimen, and number of chronic diseases (all significant, p = 0.0001). The computer program underestimated the number of chronic diseases and overestimated the number of daily doses. The level of agreement between the computer program and chart review for patient noncompliance was low (Kappa = 0.38), with the computer more likely to indicate a patient was noncompliant. A high level of agreement was seen between the computer program and chart review for the presence of a drug requiring TDM (Kappa = 0.83). For all six criteria, the computer program had a sensitivity of 65.7% and specificity of 88.2%. CONCLUSIONS: When compared with medical records, the use of this program to evaluate electronic pharmacy data can be efficient to screen large numbers of patients who may be at high risk for drug-related problems. This method may be useful for clinical pharmacists in providing pharmaceutical services to patients who are most likely to benefit.     

Transforming care at the bedside: an ambulatory model for improving the patient experience

Transforming Care at the Bedside is a nationwide effort to design a model for improving care to hospitalized patients. With the projected growth of ambulatory services, it is increasingly important to focus on potential methods to increase patient satisfaction and care delivery improvement in the outpatient setting, as well. The authors describe the University of Pittsburgh Medical Center Hillman Cancer Center's adaptation of the Transforming Care at the Bedside care delivery improvement model to its ambulatory services arena and its promising results.     

Processes of adjustment to end-of-life losses: a reintegration model

The processes surrounding psychological adjustment to losses due to advancing and end-stage illness have not been well delineated. While adjustment to losses due to death are often thought of as the bereaved's lot, dying persons experience multiple, accumulating, and profound losses of functions, abilities, roles, and relationships and therefore have to adjust as well. Many people who are facing death in the near future negotiate these losses, still achieving quality of life in all dimensions. Others fare less well. It is hard to intervene helpfully without a clear understanding of how either trajectory occurs. Building from current literature on loss and adjustment, we describe a conceptual framework of key adjustment processes that allow for quality of life during terminal illness. We term this the reintegration model. It has comprehension, creative adaptation and reintegration components, each involving the physical, psychological, social, and existential domains in ways that are characteristic of the needs, tasks and options available to a seriously ill and dying person. In this paper, we discuss the model, focusing on normal adjustment processes, and describe the implications of the framework for the dying person, caregivers, and the palliative care team.     

Children's adjustment to parental cancer: a theoretical model development

There is growing empirical evidence that various child and family factors are associated with children's reactions to parental cancer. Children having parents with cancer may respond to parental cancer in different ways in terms of bonadjustment and maladjustment. Children's maladjustment to this pervasive stressor is manifested by a wide variety of physiologic, psychologic, and behavioral stress responses. To date, research on children's adjustment to parental cancer has focused almost exclusively on documenting children's adjustment problems and on describing simple, direct association between the characteristics of children and/or their families, and children's adjustment. The gap in research and clinical practice lies in the lack of a comprehensive model to illuminate children's coping with parental cancer and to guide intervention programs. Based on a synthesis of the literature, this article proposes a model that specifies the relationships among the stressor of having a parent with cancer, moderators and mediator variables, and adjustment. This model can serve as a basis for future research and intervention programs.