Mamta Puppala

METEOR: An Enterprise Health Informatics Environment to Support Evidence-Based Medicine

Goal: The aim of this paper is to propose the design and implementation of next-generation enterprise analytics platform developed at the Houston Methodist Hospital (HMH) system to meet the market and regulatory needs of the healthcare industry. Methods: For this goal, we developed an integrated clinical informatics environment, i.e., Methodist environment for translational enhancement and outcomes research (METEOR). The framework of METEOR consists of two components: the enterprise data warehouse (EDW) and a software intelligence and analytics (SIA) layer for enabling a wide range of clinical decision support systems that can be used directly by outcomes researchers and clinical investigators to facilitate data access for the purposes of hypothesis testing, cohort identification, data mining, risk prediction, and clinical research training. Results: Data and usability analysis were performed on METEOR components as a preliminary evaluation, which successfully demonstrated that METEOR addresses significant niches in the clinical informatics area, and provides a powerful means for data integration and efficient access in supporting clinical and translational research. Conclusion: METEOR EDW and informatics applications improved outcomes, enabled coordinated care, and support health analytics and clinical research at HMH. Significance: The twin pressures of cost containment in the healthcare market and new federal regulations and policies have led to the prioritization of the meaningful use of electronic health records in the United States. EDW and SIA layers on top of EDW are becoming an essential strategic tool to healthcare institutions and integrated delivery networks in order to support evidence-based medicine at the enterprise level.

Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods

A key challenge to mining electronic health records for mammography research is the preponderance of unstructured narrative text, which strikingly limits usable output. The imaging characteristics of breast cancer subtypes have been described previously, but without standardization of parameters for data mining.

Early clearance vs persistence of de novo donor-specific antibodies following lung transplantation

The natural history of de novo donor‐specific antibodies (dnDSA) after lung transplantation is not well‐described. We sought to determine the incidence and risk factors associated with dnDSA and compare outcomes between recipients with transient (or isolated) vs persistent dnDSA after transplantation.

Data security and privacy management in healthcare applications and clinical data warehouse environment

Health Information is considered the most sensitive information associated to an individual. Even though numerous suitable policies, guidelines, and compliance requirements are in place to safeguard health information, privacy and security breach remains key issues for electronic healthcare systems. In this paper we focus on these issues and propose a security and privacy model implemented in Methodist Environment for Translational and Outcomes Research (METEOR). METEOR was developed at Houston Methodist Hospital and consists of two components: the enterprise data warehouse (EDW) and a software intelligence and analytics (SIA) layer. This model indicates that patient privacy is best protected by implementing a systematic mix of technologies and best practices such as technical de-identification of data, restrictive data access, and security measures in the underlying technical platforms. Our results suggest that the proposed security model make data security compromise and unauthorized access of protected patient health information extremely improbable.

A smartphone app framework for segmented cancer care coordination

Complex cancer care requires careful coordination, but resource limitations result in lack of effective coordinated follow-up services. Recent advances in smartphones offer great opportunities for better segmentation of patient populations for cost-effective, targeted care coordination and monitoring or surveillance of cancer patients. This paper presents a framework of a smartphone app that provides such risk assessment and follow-up care monitoring services. This mHealth app framework includes three functional modules: a natural language processing module based on Bayesian model to extract relevant information from free text or medical reports; a cancer risk calculator that uses support vector machine classification to assess the medical risks of cancer patients based on the information extracted; and a health care monitor that provides timely care coordination to high risk cancer patients. The experimental results validate mHealth as a reliable medical risk assessment for post-surgical cancer patients and an effective health care monitoring service for cancer care coordination.

QUALITY IMPROVEMENT PROJECT TO REDUCE COPD READMISSION RATE IN MEDICARE PATIENTS USING A MULTIDISCIPLINARY PROTOCOL-BASED CARE PLAN

METHODS: Beginning in 2016, all patients admitted to HMH with the primary diagnosis of AECOPD had a standardized care plan based on the Global Initiative for Chronic Obstructive Lung Disease guideline implemented prior to hospital discharge. Patients with a concurrent diagnosis of congestive heart failure exacerbation, active lung cancer or history of a lung transplant were excluded. The project involved physicians, nurses, case managers, social workers, respiratory therapists, project coordinators and the Houston Methodist Research Institute. Moreover, in 2017, a multidisciplinary group met weekly to identify high risk patients (having >50% likelihood of readmission based on internally developed software, ReAdmit app) and offered focused care. The interventions included diagnostics, medical treatments, nutrition, teaching, psychosocial assessment, discharge planning and outpatient follow up plans. The utilization of the care plan was at the discretion of the attending physician, and every hospitalist in our hospital was educated and encouraged to follow the plan. The intervention was applied to all patients; this study we focused on Medicare patients. We obtained baseline readmission data (2011–2015) and compared with the intervention period (2016 and 2017). The data was analyzed using Student’s t-test.

Deep learning analytics for diagnostic support of breast cancer disease management

Breast cancer continues to be one of the leading causes of cancer death among women. Mammogram is the standard of care for screening and diagnosis of breast cancer. The American College of Radiology developed the Breast Imaging Reporting and Data System (BI-RADS) lexicon to standardize mammographic reporting to assess cancer risk and facilitate biopsy decision-making. However, because substantial inter-observer variability remains in the application of the BI-RADS lexicon, including inappropriate term usage and missing data, current biopsy decision-making accuracy using the unstructured free text or semi-structured reports varies greatly. Hence, incorporating novel and accurate technique into breast cancer decision-making data is critical. Here, we combined natural language processing and deep learning methods to develop an analytic model that targets well-characterized and defined specific breast suspicious patient subgroups rather than a broad heterogeneous group for diagnostic support of breast cancer management.

Abstract P5-11-12: MOCHA: An institution-based care coordination app for post-hospitalization breast cancer patients

Purpose: Hospitals face many challenges in effective care coordination for post-surgery breast cancer patients, especially with scarce resources and limited availability of nurse navigators for care transition and post-hospitalization follow up. Mobile health provides an inexpensive and convenient means of real time care monitoring and communication between patients and care providers. Nevertheless, most current health apps focus on individual consumers and gather information from their daily lives, but do not integrate with clinical workflow or capture physiological and activity data into electronic medical record for real-time monitoring, patient surveillance, and professional care. To fill this gap, we have developed and implemented MOCHA (MethOdist Hospital Cancer Health Application), a coordinated care mobile app for post-hospitalization breast cancer patients from the perspective of a primary care institution. Methods: MOCHA supports both iOS and Android platforms and contains two main modules: health care monitoring and data communication, designed together with the physicians and nurses of the Houston Methodist Cancer Center. The Health care monitoring module aims to support real-time monitoring of the post-discharge medical state of breast cancer patients. Physicians can monitor the daily food intake and activities for patients and provide advice to patients in real-time. The data communication module was developed to safely exchange the care coordination data with the hospital electronic medical record or data warehouse. Communication between the patient and the physician can be via an in-house protocol or an open data exchange standard Fast Healthcare Interoperability Resources (FHIR), that describes data format and elements for exchanging electronic health records. Our communication module uses https-based protocol to exchange the structured data with the FHIR resource server. Implementation: To validate the MOCHA app, we collaborated with the oncologists and dietitians at the Houston Methodist Cancer Center, who provided breast cancer patients for post-surgery care coordination. Our app exchanges health care data in real time with our hospital9s clinical data warehouse. MOCHA searches Nutritionix food database for nutritional information and uses personal trackers such as Fitbit for patients9 daily activities with their authorization. The app sends patients9 daily burned calories into our clinical data warehouse. During the evaluation period, the physician communicates with cancer patients daily. In addition, every patient has a bi-weekly physical examination, and all examination results are shown in the app. After the experimental evaluation, the physician will access the data warehouse and analyze the test data in order to improve the quality of care coordination. The experimental clinical evaluation is ongoing, and we will report the results once the study is completed. Conclusion: MOCHA app provides health care monitoring and secure communication functions with interface with clinical data warehouse. The technical evaluation shows that the proposed methods are robust and efficient in support of care coordination for post-surgery cancer patients. Citation Format: He T, Ogunti R, Yu X, Puppala M, Chen S, Mancuso J, Stephen W. MOCHA: An institution-based care coordination app for post-hospitalization breast cancer patients [abstract]. In: Proceedings of the 2016 San Antonio Breast Cancer Symposium; 2016 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2017;77(4 Suppl):Abstract nr P5-11-12.

Comparison of Direct Patient Care Costs and Quality Outcomes of the Teaching and Non-Teaching Hospitalist Services at a Large Academic Medical Center

Purpose To compare costs of care and quality outcomes between teaching and nonteaching hospitalist services, while testing the assumption that resident-driven care is more expensive. Method Records of inpatients with the top 20 Medicare Severity Diagnosis-Related Groups admitted to the University Teaching Service (UTS) and nonteaching hospitalist service (NTHS) at Houston Methodist Hospital from 2014–2015 were analyzed retrospectively. Direct costs of care, length of stay (LOS), in-hospital mortality (IHM), 30-day readmission rate (30DRR), and consultant utilization were compared between the UTS and NTHS. Propensity score matching and case mix index (CMI) were used to mitigate differences in baseline characteristics. To compare outcomes between matched groups, the Wilcoxon rank sum test and chi-square test were used. A sensitivity analysis was conducted using multivariable regression analysis. Results From the overall study population of 8,457 patients, 1,041 UTS and 3,123 NTHS patients were matched. CMI was 1.07 for each group. The UTS had lower direct costs of care per case (

IN HOSPITAL USE OF NON-STEROIDAL ANTI-INFLAMMATORY AGENTS IN PATIENTS WITH A PRINCIPAL DIAGNOSIS OF HEART FAILURE IS ASSOCIATED WITH INCREASED LENGTH OF STAY AND 30-DAY READMISSION RATE

5,028 vs.