Health care costs of case management for frequent users of the emergency department: Hospital and insurance perspectives

Leveraging graph neural networks for supporting automatic triage of patients

Patient triage is crucial in emergency departments, ensuring timely and appropriate care based on correctly evaluating the emergency grade of patient conditions. Triage methods are generally performed by human operator based on her own experience and information that are gathered from the patient management process. Thus, it is a process that can generate errors in emergency-level associations. Recently, Traditional triage methods heavily rely on human decisions, which can be subjective and prone to errors. A growing interest has recently been focused on leveraging artificial intelligence (AI) to develop algorithms to maximize information gathering and minimize errors in patient triage processing. We define and implement an AI-based module to manage patients' emergency code assignments in emergency departments. It uses historical data from the emergency department to train the medical decision-making process. Data containing relevant patient information, such as vital signs, symptoms, and medical history, accurately classify patients into triage categories. Experimental results demonstrate that the proposed algorithm achieved high accuracy outperforming traditional triage methods. By using the proposed method, we claim that healthcare professionals can predict severity index to guide patient management processing and resource allocation.

Understanding the experience in the healthcare system of non-migrant and migrant frequent users of the emergency department in French-speaking Switzerland: a comparative qualitative study

BACKGROUND

Previous research revealed the vulnerability of frequent users of emergency department (FUED) because of concomitant medical, psychological and social issues. Case management (CM) provides FUED with effective medical and social support, however, the heterogeneity of this population has highlighted the need to explore the specific needs of FUED subpopulations. In response, this study aimed to explore qualitatively the lived experience of migrant and non-migrant FUED in the healthcare system to identify unmet needs.

METHODS

Adult migrant and non-migrant FUED (≥ 5 visits in the ED in the past 12 months) were recruited in a Swiss university hospital to collect qualitative data on their experience within the Swiss health system. Participants were selected based on predefined quotas for gender and age. Researchers conducted one-on-one semistructured interviews until reaching data saturation. Inductive conventional content analysis was used to analyse qualitative data.

RESULTS

In total, 23 semistructured interviews were conducted (11 migrant FUED and 12 non-migrant FUED). Four main themes emerged from the qualitative analysis: (1) self-evaluation of the Swiss healthcare system; (2) orientation within the healthcare system; (3) relationship with caregivers and (4) perception of own health. While both groups were overall satisfied with the healthcare system and care provided, migrant FUED reported language and financial barriers to access it. Both groups expressed overall satisfaction over their relationship with healthcare professionals, although migrant FUED reported a feeling of illegitimacy to consult the ED based on social status, whereas non-migrant FUED felt more often the need to justify their use of the ED. Finally, migrant FUED perceived their own health to be affected by their status.

CONCLUSION

This study highlighted difficulties specific to subpopulations of FUED. For migrant FUED, these included access to care and impact of migrant status on own health. Adapting CM to the specific needs of migrant FUED could help reduce their vulnerability.

Patient Perspectives on the Cost of Hand Surgery

BACKGROUND

Health-care expenditures in the U.S. are continually rising, prompting providers, patients, and payers to search for solutions to reduce costs while maintaining quality. The present study seeks to define the out-of-pocket price that patients undergoing hand surgery are willing to pay, and also queries the potential cost-cutting measures that patients are most and least comfortable with. We hypothesized that respondents would be less accepting of higher out-of-pocket costs.

METHODS

A survey was developed and distributed to paid, anonymous respondents through Amazon Mechanical Turk. The survey introduced 3 procedures: carpal tunnel release, cubital tunnel release, and open reduction and internal fixation of a distal radial fracture. Respondents were randomized to 1 of 5 out-of-pocket price options for each procedure and asked if they would pay that price. Respondents were then presented with various cost-saving methods and asked to select the options that made them most uncomfortable, even if those would save them out-of-pocket costs.

RESULTS

There were 1,408 respondents with a mean age of 37 years (range, 18 to 74 years). Nearly 80% of respondents were willing to pay for all 3 of the procedures regardless of which price they were presented. Carpal tunnel release was the most price-sensitive, with rejection rates of 17% at the highest price ($3,000) and 6% at the lowest ($250). Open reduction and internal fixation was the least price-sensitive, with rejection rates of 11% and 6% at the highest and lowest price, respectively. The use of older-generation implants was the least acceptable cost-cutting measure, at 50% of respondents.

CONCLUSIONS

The present study showed that most patients are willing to pay a considerable amount of money out of pocket for hand surgery after the condition, treatment, and outcomes are explained to them. Furthermore, respondents are hesitant to sacrifice advanced technology despite increased costs.

Health care providers' perception of the frequent emergency department user issue and of targeted case management interventions: a cross-sectional national survey in Switzerland

Background

Frequent users of emergency departments (FUEDs) (≥5 ED visits/year) represent a vulnerable population with complex needs accounting for a significant number of emergency department (ED) consultations, thus contributing to EDs overcrowding. Research exploring ED staff perceptions of FUEDs is scarce.

Objectives

The current study aimed to evaluate in ED staff a) the extent to which FUEDs are perceived as an issue; b) their perceived levels of knowledge and understanding of FUEDs; c) levels of perceived usefulness of case management (CM) and interest in implementing this intervention in their ED service.

Methods

Head physicians of the EDs at all public hospitals in Switzerland (of various level of specialization) were sent a 19-item web-based survey, pilot tested prior to its dissemination. The head physicians were asked to forward the survey to ED staff members from different health professional backgrounds.

Results

The hospital response rate was 81% (85/106). The exploitable hospital response rate was 71% (75/106 hospitals) including 208 responding health professionals. Issues and difficulties around FUEDs were perceived as important by 64% of respondents. The perceived frequency of being confronted with FUEDs was higher among nurses in more specialized EDs. In total, 64% of respondents felt poorly informed about FUEDs, nurses feeling less informed than physicians. The understanding of FUEDs was lower in the French-Italian-speaking parts (FISP) of Switzerland than in the German-speaking part. Eighty-one percent of respondents had no precise knowledge of FUED-related interventions. The perceived usefulness of CM interventions after receiving explanations about it was high (92%). However, the overall level of interest for CM implementation was 59%. The interest in CM by physicians was low across all regions and ED categories. Nurses, on the other hand, showed more interest, especially those in EDs of high specialization.

Conclusions

The majority of ED staff reported being confronted with FUEDs on a regular basis. Staff perceived FUEDs as a vulnerable population, yet, they felt poorly informed about how to manage the issue. The majority of ED staff thought a CM intervention would be useful for FUEDs, however there appears to be a gap in their desire or willingness to implement such interventions.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12873-020-00397-w.

Tracing frequent users of regional care services using emergency medical services data: a networked approach

OBJECTIVES

This study shows how a networked approach relying on 'real-world' emergency medical services (EMS) records might contribute to tracing frequent users of care services on a regional scale. Their tracing is considered of importance for policy-makers and clinicians, since they represent a considerable workload and use of scarce resources. While existing approaches for data collection on frequent users tend to limit scope to individual or associated care providers, the proposed approach exploits the role of EMS as the network's 'ferryman' overseeing and recording patient calls made to an entire network of care providers.

DESIGN

A retrospective study was performed analysing 2012-2017 EMS calls in the province of Drenthe, the Netherlands. Using EMS data, benefits of the networked approach versus existing approaches are assessed by quantifying the number of frequent users and their associated calls for various categories of care providers. Main categories considered are hospitals, nursing homes and EMS.

SETTING

EMS in the province of Drenthe, the Netherlands, serving a population of 491 867.

PARTICIPANTS

Analyses are based on secondary patient data from EMS records, entailing 212 967 transports and 126 758 patients, over 6 years (2012-2017).

RESULTS

Use of the networked approach for analysing calls made to hospitals in Drenthe resulted in a 20% average increase of frequent users traced. Extending the analysis by including hospitals outside Drenthe increased ascertainment by 28%. Extending to all categories of care providers, inside Drenthe, and subsequently, irrespective of their location, resulted in an average increase of 132% and 152% of frequent users identified, respectively.

CONCLUSIONS

Many frequent users of care services are network users relying on multiple regional care providers, possibly representing inefficient use of scarce resources. Network users are effectively and efficiently traced by using EMS records offering high coverage of calls made to regional care providers.

Case management programs in emergency department to reduce frequent user visits: a systematic review

BACKGROUND AND AIM

Inappropriate visits to the Emergency Department (ED) by frequent users (FU) are a common phenomenon because this service is perceived as a rapid and concrete answer to any health and social issue not necessarily related to urgent matters. Could Case Management (CM) programs be a suitable solution to address the problem? The purpose is to examine how CM programs are implemented to reduce the number of FU visits to the ED.

METHODS

PubMed, CINAHL and EMBASE were consulted up to December 2018. This review follows PRISMA guidelines for systematic review, as first outcomes were considered the impact of CM interventions on ED utilization, costs and composition of teams.

RESULTS

Fourteen studies were included and they showed patients with common characteristics but the FU definition wasn't the same. Twelve studies provided a reduction of ED utilization and seven studies a cost reduction. The main tool used is the individual care plan with telephone contact, supportive group therapy, facilitated contacts with healthcare providers and informatics system for immediate identification. The CM team composition is heterogeneous, even if nurses are considered the most used professional figures.

CONCLUSIONS

In contrast with a standardized method, a customized approach of CM program helps frequent users in finding an appropriate answer to their needs, thus decreasing inappropriate visits to the ED.

Implementing a case management intervention for frequent users of the emergency department (I-CaM): an effectiveness-implementation hybrid trial study protocol

Background

ED overcrowding represents a significant public health problem in developed countries. Frequent users of the emergency departments (FUEDs; reporting 5 or more ED visits in the past year) are often affected by medical, psychological, social, and substance use problems and account for a disproportionately high number of ED visits. Past research indicates that case management (CM) interventions are a promising way to reduce ED overcrowding and improve FUEDs’ quality of life. There is, however, very limited knowledge about how to disseminate and implement this intervention on a large scale to diverse clinical settings, including community hospitals and non-academic centers. This paper describes the protocol of a research project aiming to implement a CM intervention tailored to FUEDs in the public hospitals with ED in the French-speaking region of Switzerland and evaluate both the implementation process and effectiveness of the CM intervention.

Methods

This research project uses a hybrid study design assessing both implementation and clinical outcomes. The implementation part of the study uses mixed methods a) to describe quantitatively and qualitatively factors that influence the implementation process, and b) to examine implementation effectiveness. The clinical part of the study uses a within-subject design (pre-post intervention) to evaluate participants’ trajectories on clinical variables (e.g., quality of life, ED use) after receiving the CM intervention. We designed the study based on two implementation science frameworks. The Generic Implementation Framework guided the overall research protocol design, whereas the RE-AIM (reach, efficacy, adoption, implementation and maintenance) framework guided the implementation and effectiveness evaluations.

Discussion

This research project will contribute to implementation science by providing key insights into the processes of implementing CM into broader practice. This research project is also likely to have both clinical and public health implications.

Trial registration

NCT03641274, Registered 20 August 2018.