Analysis of length of hospital stay using electronic health records: A statistical and data mining approach

Baek, Hyunyoung; Cho, Minsu; Kim, Seok; Hwang, Hee; Song, Minseok; Yoo, Sooyoung

doi:10.1371/journal.pone.0195901

Cited by 230 publications

(173 citation statements)

References 26 publications

Supporting

Mentioning

162

Contrasting

Unclassified

Order By: Relevance

“…Those with comorbid anxiety and depression experienced hospital stays nearly 72% longer than those with neither condition. As discussed elsewhere (Baek et al, 2018; Bueno et al, 2010; Rotter et al, 2010), longer hospital stays can increase risks of opportunistic infections and side effects of medication, as well as have deleterious effects on treatment outcomes and mortality rates. In addition, longer hospital stays are associated with increased medical costs and decreased bed turnover rates (Bueno et al, 2010; Rotter et al, 2010).…”

Section: Discussionmentioning

confidence: 99%

Healthcare use and costs in adult cancer patients with anxiety and depression

Decastro

Schwab

Tiamson-Kassab

et al. 2020

Depression and Anxiety

View full text Add to dashboard Cite

Objective Anxiety and depression are common in individuals with cancer and may impact healthcare service use and costs in this population. This study examined the effects of anxiety alone, depression alone, and comorbid anxiety and depressive disorder on healthcare use and costs among patients with cancer. Method This was a retrospective cohort analysis of administrative data of patients aged 18 or older with an International Classification of Diseases, Ninth Revision diagnosis of cancer. Key outcomes were any visit to emergency department (ED), any inpatient hospitalization, length of hospital stays, and annual healthcare costs 1 year from cancer diagnosis. Results A total of 13,426 patients were included. Relative to patients with neither anxiety nor depression, those with anxiety alone, depression alone, or comorbid anxiety and depression were more likely to experience an ED visit and be hospitalized. Length of hospital stays were also longer and annual healthcare costs were significantly higher in all three clinical groups. Conclusions Cancer patients with anxiety and depression were at greater risk for ED visits and hospitalizations, experienced longer hospital stays, and accrued higher healthcare costs. Future researchers should determine whether screening and treating comorbid anxiety and depression may decrease healthcare utilization and improve turnover wellbeing among cancer patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Healthcare use and costs in adult cancer patients with anxiety and depression

Decastro

Schwab

Tiamson-Kassab

et al. 2020

Depression and Anxiety

View full text Add to dashboard Cite

show abstract

“…Two papers [16,21] were not included in Table 6, since several hundred diseases and health problems were cited and classified using ICD-9. Of the remaining 36 case studies, ICD-10 was already used in 8 papers to code the diagnosis [12,14,21,22,33,34,38,40].…”

Section: Medical Diagnosismentioning

confidence: 99%

“…For each of our selected papers, we identified at least one of the 18 high-level clinical specialties coded by SNOMED CT. For greater specificity, SNOMED CT offers further standard clinical codes for sub-specialities. In fact, Baek et al list multiple sub-specialities along with their corresponding SNOMED CT codes in their study [12]. Also, instead of Clinical specialty, another category of clinical descriptors such as the type of medical practitioner or occupation could have been considered (e.g., mapping to surgeon instead of surgical specialty).…”

Section: Clinical Specialtymentioning

confidence: 99%

“…As such, the use of standard clinical descriptors is becoming increasingly relevant, not only for clarity and comparability, but efficiency in outcome measurements such as length of stay (LOS) and financial cost. For example, in their paper, Baek et al utilized process mining techniques and statistical methods to identify the factors associated with LOS in a South Korean hospital [12]. This study is just one use case for a more detailed description of the medical context where process mining case studies could allow for future meta-studies, e.g., benchmarking LOS in different hospitals or countries, based on diagnoses while also considering other important factors like the patient encounter environment.…”

Section: Conclusion and Future Perspectivesmentioning

confidence: 99%

See 1 more Smart Citation

Towards the Use of Standardized Terms in Clinical Case Studies for Process Mining in Healthcare

Helm

Lin

Baumgartner

et al. 2020

IJERPH

View full text Add to dashboard Cite

Process mining can provide greater insight into medical treatment processes and organizational processes in healthcare. To enhance comparability between processes, the quality of the labelled-data is essential. A literature review of the clinical case studies by Rojas et al. in 2016 identified several common aspects for comparison, which include methodologies, algorithms or techniques, medical fields, and healthcare specialty. However, clinical aspects are not reported in a uniform way and do not follow a standard clinical coding scheme. Further, technical aspects such as details of the event log data are not always described. In this paper, we identified 38 clinically-relevant case studies of process mining in healthcare published from 2016 to 2018 that described the tools, algorithms and techniques utilized, and details on the event log data. We then correlated the clinical aspects of patient encounter environment, clinical specialty and medical diagnoses using the standard clinical coding schemes SNOMED CT and ICD-10. The potential outcomes of adopting a standard approach for describing event log data and classifying medical terminology using standard clinical coding schemes are further discussed. A checklist template for the reporting of case studies is provided in the Appendix A to the article.

show abstract

“…Length of hospital stay (LOS) after surgery is one of the relevant clinical outcomes measured in many clinical settings [11][12][13]. Longer LOS has been shown to be associated with patient characteristics such as age, higher morbidity, worsened frailty, increased number and severity of comorbidities and unfavorable clinical outcomes and complications [11][12][13][14][15][16]. Previous studies also showed longer LOS was associated with more infectious complications; which could lead to decreased use of immunosuppressive medications or larger amount of blood product transfusions [14,15,17].…”

Section: Introductionmentioning

confidence: 99%

Association between longer hospitalization and development of de novo donor specific antibodies in simultaneous liver–kidney transplant recipients

et al. 2019

View full text Add to dashboard Cite

Background: De novo Donor Specific Antibodies (DSA) are considered as a risk factor for the kidney allograft outcomes in recipients after simultaneous liver-kidney transplantation (SLKT). We hypothesized that length of hospital stay (LOS) might be associated with de novo DSA development of due to the increased likelihood of receiving blood transfusions with reduced immunosuppressive regimens. Methods: This study is a single-center, retrospective cohort study consisting of 85 recipients who underwent SLKT from 2009 to 2018 in our hospital. We divided the patients into two groups according to LOS [long hospital stay (L) group (LOS >14 days) and short hospital stay (S) group (LOS 14 days)]. Propensity score (PS) has been created using logistic regression to predict LOS greater than median of 14 days. The association between the presence of de novo DSA and LOS was assessed by logistic regression models adjusted for PS. Results: The mean age at transplantation of the entire cohort was 55.5 ± 10.1 years. Sixty percent of the recipients were male and Caucasian. Median LOS in (L) group was threefold longer than (S) group [L: median 30 days (IQR: 21-52), S: median 8.5 days (IQR: 7-11)]. Eight patients developed de novo DSA after SLKT (9.4%), all of them were in (L) group. Longer LOS was significantly associated with higher risk of development of de novo DSA in unadjusted (OR þ each 5 days : 1.09, 95% CI:1.02-1.16) and PS adjusted (OR þ each 5 days : 1.11, 95% CI:1.02-1.21) analysis. Conclusion: Longer hospitalization is significantly associated with the development of de novo DSA in SLKT.

show abstract

Analysis of length of hospital stay using electronic health records: A statistical and data mining approach

Cited by 230 publications

References 26 publications

Healthcare use and costs in adult cancer patients with anxiety and depression

Healthcare use and costs in adult cancer patients with anxiety and depression

Towards the Use of Standardized Terms in Clinical Case Studies for Process Mining in Healthcare

Association between longer hospitalization and development of de novo donor specific antibodies in simultaneous liver–kidney transplant recipients

Contact Info

Product

Resources

About