Leveraging electronic health record data to inform hospital resource management : A systematic data mining approach.

Early identification of resource needs is instrumental in promoting efficient hospital resource management. Hospital information systems, and electronic health records (EHR) in particular, collect valuable demographic and clinical patient data from the moment patients are admitted, which can help predict expected resource needs in early stages of patient episodes. To this end, this article proposes a data mining methodology to systematically obtain predictions for relevant managerial variables by leveraging structured EHR data. Specifically, these managerial variables are: i) Diagnosis categories, ii) procedure codes, iii) diagnosis-related groups (DRGs), iv) outlier episodes and v) length of stay (LOS). The proposed methodology approaches the problem in four stages: Feature set construction, feature selection, prediction model development, and model performance evaluation. We tested this approach with an EHR dataset of 5,089 inpatient episodes and compared different classification and regression models (for categorical and continuous variables, respectively), performed temporal analysis of model performance, analyzed the impact of training set homogeneity on performance and assessed the contribution of different EHR data elements for model predictive power. Overall, our results indicate that inpatient EHR data can effectively be leveraged to inform resource management on multiple perspectives. Logistic regression (combined with minimal redundancy maximum relevance feature selection) and bagged decision trees yielded best results for predicting categorical and numerical managerial variables, respectively. Furthermore, our temporal analysis indicated that, while DRG classes are more difficult to predict, several diagnosis categories, procedure codes and LOS amongst shorter-stay patients can be predicted with higher confidence in early stages of patient stay. Lastly, value of information analysis indicated that diagnoses, medication and structured assessment forms were the most valuable EHR data elements in predicting managerial variables of interest through a data mining approach.

Can structured EHR data support clinical coding? A data mining approach.

Structured data formats are gaining momentum in electronic health records and can be leveraged for decision support and research. Nevertheless, such structured data formats have not been explored for clinical coding, which is an essential process requiring significant manual workload in health organisations. This article explores the extent to which fully structured clinical data can support assignment of clinical codes to inpatient episodes, through a methodology that tackles high dimensionality issues, addresses the multi-label nature of coding and optimises model parameters. The methodology encompasses transformation of raw data to define a feature set, build a data matrix representation, and testing combinations of feature selection methods with machine learning models to predict code assignment. The methodology was tested with a real hospital dataset and showed varying predictive power across codes, while demonstrating the potential of leveraging structuring data to reduce workload and increase efficiency in clinical coding.

Preprocessing structured clinical data for predictive modeling and decision support. A roadmap to tackle the challenges.

BACKGROUND: EHR systems have high potential to improve healthcare delivery and management. Although structured EHR data generates information in machine-readable formats, their use for decision support still poses technical challenges for researchers due to the need to preprocess and convert data into a matrix format. During our research, we observed that clinical informatics literature does not provide guidance for researchers on how to build this matrix while avoiding potential pitfalls. OBJECTIVES: This article aims to provide researchers a roadmap of the main technical challenges of preprocessing structured EHR data and possible strategies to overcome them. METHODS: Along standard data processing stages - extracting database entries, defining features, processing data, assessing feature values and integrating data elements, within an EDPAI framework -, we identified the main challenges faced by researchers and reflect on how to address those challenges based on lessons learned from our research experience and on best practices from related literature. We highlight the main potential sources of error, present strategies to approach those challenges and discuss implications of these strategies. RESULTS: Following the EDPAI framework, researchers face five key challenges: (1) gathering and integrating data, (2) identifying and handling different feature types, (3) combining features to handle redundancy and granularity, (4) addressing data missingness, and (5) handling multiple feature values. Strategies to address these challenges include: cross-checking identifiers for robust data retrieval and integration; applying clinical knowledge in identifying feature types, in addressing redundancy and granularity, and in accommodating multiple feature values; and investigating missing patterns adequately. CONCLUSIONS: This article contributes to literature by providing a roadmap to inform structured EHR data preprocessing. It may advise researchers on potential pitfalls and implications of methodological decisions in handling structured data, so as to avoid biases and help realize the benefits of the secondary use of EHR data.

Mobile health platform for pressure ulcer monitoring with electronic health record integration.

Pressure ulcers frequently occur in patients with limited mobility, for example, people with advanced age and patients wearing casts or prostheses. Mobile information communication technologies can help implement ulcer care protocols and the monitoring of patients with high risk, thus preventing or improving these conditions. This article presents a mobile pressure ulcer monitoring platform (mULCER), which helps control a patient's ulcer status during all stages of treatment. Beside its stand-alone version, it can be integrated with electronic health record systems as mULCER synchronizes ulcer data with any electronic health record system using HL7 standards. It serves as a tool to integrate nursing care among hospital departments and institutions. mULCER was experimented with in different mobile devices such as LG Optimus One P500, Samsung Galaxy Tab, HTC Magic, Samsung Galaxy S, and Samsung Galaxy i5700, taking into account the user's experience of different screen sizes and processing characteristics.

Why management and leadership education for internists?

Around the world, there is an increasing need for more efficiency in healthcare alongside cost containment. Internal medicine physicians are in a pivotal position in this regard. In many countries, they act as bridges between ambulatory/continuity of care systems and hospital-based intensive care and sophisticated therapies. Within the medical field, they often bridge gaps between many specialities increasingly required to provide modern medical care. These skills of managing complex environments, being sensitive to health economics and using large amounts of information, are not normally taught or developed in programmes of internal medicine. While some skills are natural and acquired through practice, other skills would benefit from insights from the fields of management. On the other hand, it seems critical to have internists playing a leading role in the future care of aging populations, and they are the most likely to understand the needs of these multi-pathology cases. On a practical level, internists face the daily challenges of engaging and leading as many people as possible to provide the best care; this requires very good leadership, negotiation, team-working and change-management skills, all of which can be vastly enhanced with specific education initiatives that are targeted and customised to physicians' needs. Management education for internists should be "spiral", starting from medical school and expanding to incorporate issues as the physician matures into new activities and responsibilities. In practical terms, current internists and residents of internal medicine can be brought into contact with such education by a combination of workshops as well as residential and online courses.

What explains doctors' usage of Mobile Information and Communication Technologies? A comparison of US and Portuguese hospitals.

Doctors, either as a result of individual initiative or departmental policy, may use a number of different mobile computers. The relationship between device ownership/provision and usage is, however, rarely discussed. This paper therefore presents survey data (N=267) on mobile computer ownership and use by doctors in two Portuguese and two US hospitals, considering both devices owned by individuals and those supplied by the hospital. The results show that ownership is not clearly related to either usage pattern or frequency of use. Providing handheld computers also did not lead to higher number of users, higher frequency of use or significant differences in tasks carried out. Nevertheless, doctors owning handhelds alone or in combination with laptops used them more frequently than those using laptops alone. Differences in usage pattern proportions rather than demographics were a better indication of differences in usage frequencies and the tasks for which MICT devices were being used.

Perspectives on management education: an exploratory study of UK and Portuguese medical students.

Healthcare management is becoming extremely important and large health organizations face increasing demands for leadership and system change. The role of doctors is pivotal but their relationship with management issues and practice has been a matter of long-lasting debate. The aim of this research was to establish opinions of medical students and other medical educational stakeholders on the value and structure of a management and leadership course in medical school. A survey of undergraduate medical students from two medical schools (n = 268) was carried out, and quantitative and qualitative data were analysed and compared with opinions collected from interviews with hospital managers and clinical professors. Portuguese medical students attributed higher relevance to leadership/management education than their UK counterparts. For both groups, such a course would be best: (1) situated in the clinical years, (2) optional and (3) one term/semester long. Main topics desired were 'Managing people/team management'; 'National Health Service'; 'Doctors and Leadership', 'Costs/prices and resource management'. In conclusion, leadership/management education is perceived as relevant but its inclusion in the medical curriculum as well as its content needs careful consideration. Education in informatics and knowledge management would also provide a positive contribution to professional development but is scarcely appreciated at present.