Patient falls during hospitalization can lead to severe injuries and remain one of the most vexing patient-safety problems facing hospitals. They lead to increased medical care costs, lengthened hospital stays, more litigation, and even death. Existing methods and technology to address this problem mostly focus on stratifying inpatients at risk, without predicting fall severity or injuries. Here, a retrospective cohort study was designed and performed to predict the severity of inpatient falls, based on a machine learning classifier integrating multi-view ensemble learning and model-based missing data imputation method. As input, over two thousand inpatient fall patients’ demographic characteristics, diagnoses, procedural data, and bone density measurements were retrieved from the HMH clinical data warehouse from two separate time periods. The predictive classifier developed based on multi-view ensemble learning with missing values (MELMV) outperformed other three baseline models; achieved a cross-validated AUC of 0.713 (95% CI, 0.701–0.725), an AUC of 0.808 (95% CI, 0.740–0.876) on the separate testing set. Our studies show the efficacy of integrative machine-learning based classifier model in dealing with multi-source patient data, which in this case delivers robust predictive performance on the severity of patient falls. The severe fall index provided by the MELMV classifier is calculated to identify inpatients who are at risk of having severe injuries if they fall, thus triggering additional steps of intervention to prevent a harmful fall, beyond the standard-of-care procedure for all high-risk fall patients.

Purpose To describe the development of a multidisciplinary anticoagulant safety taskforce (ASTF) to address anticoagulation-related issues across the medication-use system. Summary Oral and parenteral anticoagulants have been classified as high-alert medications because of their potential for harm. Errors at the point of prescribing, monitoring, and administering therapy have been noted in safety literature. Our hospital system, which includes 1 academic medical center, 6 community hospitals, and 1 long-term care facility, designed a multidisciplinary ASTF to address anticoagulation-related issues. The ASTF used the 2017 Institute for Safe Medication Practices (ISMP) Medication Safety Self-Assessment for Antithrombotic Therapy as the primary tool for reviewing current practices, performing gap analyses, and identifying our greatest areas of opportunity. The top 8 best practice elements related to anticoagulant use were identified for initial efforts of ASTF activity. Meetings were led by a medication safety pharmacist who reviewed process opportunities and actions to address gaps. The hospital chief quality and patient safety officer and the vice president of quality were the executive sponsors of the ASTF. Key stakeholders such as the medication safety committee chair and the president of the medical staff were instrumental in leading the initiative. Recommendations from the ASTF were reviewed and approved by the system medication safety committee and the system pharmacy and therapeutics committee to support system-wide implementation. The ASTF accomplished more than initially planned within its first year. Error mitigation occurred through policy revisions, order set development and modification, and implementation of practice changes to comply with each best practice. The ISMP antithrombotic self-assessment score improved from 67% to 87%, surpassing the initially targeted score of 75%. To overcome implementation barriers with the electronic health record, we enlisted support from our informatics leadership to leverage information technology. Overall, the success of the taskforce was attributed to the teamwork and leadership of key individuals within the organization. Conclusion Leveraging interest from key stakeholders across multiple disciplines with an established assessment tool was key in developing a productive and successful ASTF. The group came together to evaluate anticoagulant-related issues and implement sustainable changes to decrease anticoagulation error potential.

Knowing the areas of service, actions, and parameters that can influence patient perception about a service provided can help hospital executives and healthcare workers to devise improvement plans, leading to higher patient satisfaction. To identify inpatient satisfaction determinants, assess their relationships with hospital variables, and improve patient satisfaction through interventions. We studied the inpatient population of an eight-hospital tertiary medical center in 2015. The satisfaction determinants were based on the Hospital Consumer Assessment of Healthcare Providers and Systems (HCAHPS) survey answers and included clinical and organizational variables. Interventions began at the end of 2016 included bedside care coordination rounds (BCCR), medications best practices alert (BPA), connect transitions post-discharge calls (CONNECT Transitions) and a framework for provider-patient interactions called AIDET (Acknowledge, Introduce, Duration, Explain, and Thank). Substantial impact upon patient satisfaction was observed after the introduction of these interventions. Three groups were identified: high satisfaction, which correlated with race, surgery, and cancer care; low satisfaction, correlated with elderly, emergency room, intensive care unit, chronic obstructive pulmonary disease, and vascular diseases; and neutral, correlated with hospital-acquired complications, several diagnostic procedures, and medical care delay. Significant improvements in the 3 groups were achieved with interventions that optimize care provider interactions with patients and their families. Based on the HCAHPS-based analysis, we implemented new measures and programs for addressing coordination of care, improving patient safety, reducing the length of stay, and ultimately improving patient satisfaction.