Interpretable Predictive Models for Knowledge Discovery from Home‐Care Electronic Health Records

Westra, Bonnie L.; Dey, Sanjoy; Fang, Gang; Steinbach, Michael; Kumar, Vipin; Oancea, Cristina; Savik, Kay; Dierich, Mary

doi:10.1260/2040-2295.2.1.55

Cited by 12 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding is powerful, given that the mandate for implementing “standards” alone is not sufficient to bring the desired consistency and format of information needed by frontline EHR users to help them stay on the same page. Scherb (2002) and Westra and colleagues (Westra, Dey, et al., 2011; Westra, Savik, et al., 2011) provide excellent examples of the problems associated with implementing standardized terminologies without regard for the other standards needed to bring intended value. Scherb found that the architecture of a database structure severely constrained their ability to analyze and generate visualizations of the relationships among the collected data elements in spite of use of standardized terminologies.…”

Section: Discussionmentioning

confidence: 99%

“…Scherb found that the architecture of a database structure severely constrained their ability to analyze and generate visualizations of the relationships among the collected data elements in spite of use of standardized terminologies. Westra and colleagues (Westra, Dey, et al., 2011; Westra, Savik, et al., 2011) found in conducting statistical and data mining exercises that much of the data gathered by different EHR systems, all of which used the same standardized terminologies, were not useful due to differences in the way the EHR systems collected and stored the data elements.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Maintaining a Consistent Big Picture: Meaningful Use of a Web‐based POC EHR System

Keenan

Yakel

Yao

et al. 2012

Int J of Nursing Knowl

View full text Add to dashboard Cite

Objective To test the hypothesis that HANDS “big picture summary” can be implemented uniformly across diverse settings and result in positive RN and plan of care (POC) data outcomes across time. Design In a longitudinal, multi-site, full test design, a representative convenience sample of 8 medical-surgical units from 4 hospitals (1 university, 2 large community, and 1 small community) in one Midwestern state implemented the HANDS intervention for 24 (4 units) or 12 (4 units) months. Measurements 1) RN outcomes - percentage completing training, satisfaction with standardized terminologies, perception of HANDS usefulness, POC submission compliance rate. 2) POC data outcomes – validity (rate of optional changes/episode); reliability of terms and ratings; and volume of standardized data generated. Results 100% of the RNs who worked on the 8 study units successfully completed the required standardized training; all units selected participated for the entire 12- or 24-month designated period; compliance rates for POC entry at every patient handoff were 78% to 92%; reliability coefficients for use of the standardized terms and ratings were moderately strong; the pattern of optional POC change per episode declined but remained reasonable across time; the nurses generated a database of 40,747 episodes of care. Limitations Only RNs and medical-surgical units participated. Conclusion It is possible to effectively standardize the capture and visualization of useful “big picture” healthcare information across diverse settings. Findings offer a viable alternative to the current practice of introducing new health information layers that ultimately increase the complexity and inconsistency of information for front line users.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Maintaining a Consistent Big Picture: Meaningful Use of a Web‐based POC EHR System

Keenan

Yakel

Yao

et al. 2012

Int J of Nursing Knowl

View full text Add to dashboard Cite

show abstract

“…Future studies should take into account that the performance of the model can be overestimated if using the entire sample for model construction. Internal validation methods, such as cross-validation, should be employed, by repeatedly partitioning the data into 10 parts, creating the model with a training set, and then validating it with a hold out data set [53].…”

Section: Discussionmentioning

confidence: 99%

Exploring the Value of Clinical Data Standards to Predict Hospitalization of Home Care Patients

Monsen¹,

Swanberg

Oancea

et al. 2012

Appl Clin Inform

View full text Add to dashboard Cite

SummaryBackground: There is a critical need to reduce hospitalizations for Medicare patients and electronic health record (EHR) home care data provide new opportunities to evaluate risk of hospitalization for patients. Objectives: The objectives of this study were to 1) develop a measure to predict risk of hospitalization among home care patients, the Hospitalization Risk Score (HRS), and 2) compare it with an existing severity of illness measure, the Charlson Index of Comorbidity (CIC). Methods: A convenience sample of clinical data from 14 home care agencies' EHRs, representing 1,643 home care patient episodes was used for the study. The development of the HRS was based on review of the literature, and expert panel evaluation to construct the HRS. Descriptive statistics and generalized linear models were used for comparative analysis; areas under curve (AUC) values were compared for receiver operating curves (ROC), and cut points predicting hospitalization were evaluated. Results:The HRS for this sample ranged from 0 to 5.6, with a median of 1.25. The CIC for this sample ranged from 0 to 9 and with a median of 0. Nearly three fourths of the sample was hospitalized at an HRS of 2, and a CIC of 1. AUC values for ROC were 0.63 for HRS and 0.59 for the CIC. The ROC curves were significantly different (t = -7.59, p <0.003). Conclusions: This preliminary study demonstrates the potential value of the HRS using Omaha System EHR data. There was a statistically significant difference for predicting hospitalization of home care patients with the HRS versus the CIC; however the AUC values for both were low. Continued research is needed to further refine the HRS, determine whether it is more sensitive for particular subgroups of patients, and combine it with additional risk factors in understanding rehospitalization.

show abstract

“…Another popular method of interpreting complex models is given with the rule-based or decision tree based model, which both can provide nice intuitive interpretations about risk factors and their interactions [94]. Other popular techniques include visualization techniques for depicting complex clinical models into an easily digestible form [95].…”

Section: Interpretability Issues Of Pghdmentioning

confidence: 99%

Added Value from Secondary Use of Person Generated Health Data in Consumer Health Informatics

Hsueh¹,

Cheung²,

Dey³

et al. 2017

Yearb Med Inform

View full text Add to dashboard Cite

Summary Introduction: Various health-related data, subsequently called Person Generated Health Data (PGHD), is being collected by patients or presumably healthy individuals as well as about them as much as they become available as measurable properties in their work, home, and other environments. Despite that such data was originally just collected and used for dedicated predefined purposes, more recently it is regarded as untapped resources that call for secondary use. Method: Since the secondary use of PGHD is still at its early evolving stage, we have chosen, in this paper, to produce an outline of best practices, as opposed to a systematic review. To this end, we identified key directions of secondary use and invited protagonists of each of these directions to present their takes on the primary and secondary use of PGHD in their sub-fields. We then put secondary use in a wider perspective of overarching themes such as privacy, interpretability, interoperability, utility, and ethics. Results: We present the primary and secondary use of PGHD in four focus areas: (1) making sense of PGHD in augmented Shared Care Plans for care coordination across multiple conditions; (2) making sense of PGHD from patient-held sensors to inform cancer care; (3) fitting situational use of PGHD to evaluate personal informatics tools in adaptive concurrent trials; (4) making sense of environment risk exposure data in an integrated context with clinical and omics-data for biomedical research. Discussion: Fast technological progress in all the four focus areas calls for a societal debate and decision-making process on a multitude of challenges: how emerging or foreseeable results transform privacy; how new data modalities can be interpreted in light of clinical data and vice versa; how the sheer mass and partially abstract mathematical properties of the achieved insights can be interpreted to a broad public and can consequently facilitate the development of patient-centered services; and how the remaining risks and uncertainties can be evaluated against new benefits. This paper is an initial summary of the status quo of the challenges and proposals that address these issues. The opportunities and barriers identified can serve as action items individuals can bring to their organizations when facing challenges to add value from the secondary use of patient-generated health data.

show abstract

Interpretable Predictive Models for Knowledge Discovery from Home‐Care Electronic Health Records

Cited by 12 publications

References 11 publications

Maintaining a Consistent Big Picture: Meaningful Use of a Web‐based POC EHR System

Maintaining a Consistent Big Picture: Meaningful Use of a Web‐based POC EHR System

Exploring the Value of Clinical Data Standards to Predict Hospitalization of Home Care Patients

Added Value from Secondary Use of Person Generated Health Data in Consumer Health Informatics

Contact Info

Product

Resources

About