International journal of medical informatics
-
Outcomes for cancer patients have been previously estimated by applying various machine learning techniques to large datasets such as the Surveillance, Epidemiology, and End Results (SEER) program database. In particular for lung cancer, it is not well understood which types of techniques would yield more predictive information, and which data attributes should be used in order to determine this information. In this study, a number of supervised learning techniques is applied to the SEER database to classify lung cancer patients in terms of survival, including linear regression, Decision Trees, Gradient Boosting Machines (GBM), Support Vector Machines (SVM), and a custom ensemble. ⋯ Although SVM underperformed with an RMSE value of 15.82, statistical analysis singles the SVM as the only model that generated a distinctive output. The results of the models are consistent with a classical Cox proportional hazards model used as a reference technique. We conclude that application of these supervised learning techniques to lung cancer data in the SEER database may be of use to estimate patient survival time with the ultimate goal to inform patient care decisions, and that the performance of these techniques with this particular dataset may be on par with that of classical methods.
-
The emergence of online health communities broadens and diversifies channels for patient-doctor interaction. Given limited medical resources, online health communities aim to provide better treatment by decreasing medical costs, making full use of available resources and providing more diverse channels for patients. ⋯ This study contributes to both knowledge and practice. This study shows that there is channel effect in healthcare, websites' managers can encourage physicians to provide online services, especially for these physicians who do not have enough patients.
-
Recent U.S. government regulations incentivize implementation of an electronic health record (EHR) with computerized order entry and structured results display. Many institutions have also chosen to interface their EHR to their laboratory information system (LIS). Reported long-term benefits include increased efficiency and improved quality and safety. In order to successfully implement an interfaced EHR-LIS, institutions must plan years in advance and anticipate the impact of an integrated system. It can be challenging to fully understand the technical, workflow and resource aspects and adequately prepare for a potentially protracted system implementation and the subsequent stabilization. ⋯ EHR-LIS implementations have many challenges requiring institutions to adapt and develop new infrastructures. This article should be helpful to other institutions facing or undergoing a similar endeavor.
-
Since the 1990s many hospitals in the OECD countries have introduced electronic health record (EHR) systems. A number of studies have examined the factors impinging on EHR implementation. Others have studied the clinical efficacy of EHR. However, only few studies have explored the (intermediary) factors that make EHR systems conducive to quality management (QM). ⋯ The findings resonates well with previous reviews, though two factors making EHR support QM seem new, namely: political goals and strategies, and integration of guidelines for clinical conduct. Lacking EHR type specification and diversity in study method imply that there is a strong need for further research on the factors that may make EHR may support QM.
-
In health care, information technologies (IT) hold a promise to harness an ever-increasing flow of health related information and bring significant benefits including improved quality of care, efficiency, and cost containment. One of the main tools for collecting and utilizing health data is the Electronic Health Record (EHR). EHRs implementation can face numerous barriers to acceptance including attitudes and perceptions of potential users, required effort attributed to their implementation and usage, and resistance to change. Various theories explicate different aspects of technology deployment, implementation, and acceptance. One of the common theories is the Technology Acceptance Model (TAM), which helps to study the implementation of different healthcare IT applications. The objectives of this study are: to understand the barriers of EHR implementation from the perspective of physicians; to identify major determinants of physicians' acceptance of technology; and develop a model that explains better how EHRs (and technologies in general) are accepted by physicians. ⋯ The current study draws from the barriers of EHR implementation and identifies major determinants of technology acceptance among physicians. The study proposes TMTA as affording stronger explanative and predictive abilities for the health care system. TMTA paves a long overlooked gap in TAM and its descendants, which, in organizational settings, might distort construal of technology acceptance. It also explicates with greater depth the interdependence of different participants of the healthcare and complex interactions between healthcare and technologies.