Autoverification Improved Process Efficiency, Reduced Staff Workload, and Enhanced Staff Satisfaction Using a Critical Path for Result Validation

Nuanin, Sairung; Tientadakul, Panutsaya; Reesukumal, Kanit; Piyophirapong, Sudarat; Kost, Gerald J.; Pratumvinit, Busadee

doi:10.33192/smj.2020.40

Cited by 3 publications

(1 citation statement)

References 27 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding a LIS with auto-approval capability, the results are released from clinical instruments to the patient without the expert evaluation procedure. It may improve efficiency, reduce the overall turnaround time, and be accomplished within flexible regulatory frameworks [6], [7]. Ideally, it allows the analyzer to focus manual reviews on a small portion of potentially problematic specimens and test results instead of thousands of them, which can significantly reduce the total review time and effort [8], [9].…”

Section: Background and Objectivesmentioning

confidence: 99%

An Auto-Approval Approach for Laboratory Test Assessment

Mutlu

Kazezoğlu

Soylu³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Background: Auto-approval is the task of automatically evaluating the consistency of a test result throughout the laboratory information system rather than its manual evaluation by the biochemists. Most of the existing auto-approval systems rely on a rule-based solution obtained from expert knowledge. However, it is a challenging issue to produce a complete and general rule-base for every single test type. To that end, the studies have relied only on a small subset of laboratory tests. Methods: The rule-based auto-approval process was re-investigated in this study, and the rules predetermined by human experts were utilized as a pre-filtering step for grouping the laboratory test result via some common criteria. Subsequently, a machine learning-based approval method, smart-approval, was proposed to approve the tests more precisely. At this point, the expert knowledge in the rule-based pre-filtering was extended by the tendency to imitate the experts' behavior in the smart-approval step. Two novel datasets (entitled with plot and real-time datasets) containing human experts' responses to previously studied tests have been used to train the machine learning models. Results: Experiments have been handled on several machine learning models on plot dataset to obtain the trained models based on cross-validation. Here, the random forest classifier provided the best approval performance while also outperforming the approval success of existing studies in the literature. To observe the real-time performance of these trained models, they were also evaluated on real-time unseen data for 4 months. Here, random forest reaffirmed that it was the best approval model. Conclusions: The proposed auto-approval system relying on random forest can provide convincing classification performance on both of the obtained datasets. With the correct approval rate of 98.51%, it surpasses many powerful approval methods in the literature.

show abstract

Section: Background and Objectivesmentioning

confidence: 99%

An Auto-Approval Approach for Laboratory Test Assessment

Mutlu

Kazezoğlu

Soylu³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

Automation in Clinical Laboratories: A Comprehensive Bibliography Review

Fernandes,

Dos Santos,

Mercorelli

2024

2024 25th International Carpathian Control Conference (ICCC)

View full text Add to dashboard Cite

Impact of Autoverification in the Hematology Laboratory: Experience with LimasVfy

Park

Kim

et al. 2023

J Lab Med Qual Assur

View full text Add to dashboard Cite

Background:The aim of our study is to examine the performance of an algorithm used by autoverification middleware (LimasVfy; Hwasan System, Korea) in the diagnostic hematology laboratory of a single tertiary hospital in Korea. Methods: In this study, we included manually verified complete blood count (CBC) results from June 2019 to January 2020, as well as CBC results from February 2020 to September 2021 that underwent both autoverification and manual verification. The autoverification rates and turnaround time (TAT) of both datasets were compared, thereby obtaining an effective comparison between the period before and after the introduction of the autoverification system. Results: After introducing autoverification, the rates of autoverification and manual verification were 64.6% and 35.4%, respectively. Of the manually verified cases, those with delta check, panic value, flags, and critical values were 46.4%, 28.2%, 19.8%, and 5.6%, respectively. After the autoverification rule related to platelet count was modified in August 2020, the rate slightly increased from 63.9% to 64.8%, and critical value reporting rates decreased from 26.8% to 2.4%. Prior to autoverification, the median time from reception to production of results/from production of results to final reports was 9.6/35.1 minutes. After introducing autoverification, it was 10.0/39.9 minutes in manually verified cases and 3.2/0.0 minutes in autoverified cases. Total time, that is the product of total number of cases and average TAT, decreased from 350,000 to 200,000 minutes. Rate of excess TAT also decreased from 0.065% to 0.045%. Conclusions: LimasVfy would be a useful tool in reducing TAT and verification workload in the CBC testing, and this study can provide useful information in determining the introduction of autoverification systems in the setting of diagnostic hematology.

show abstract

Autoverification Improved Process Efficiency, Reduced Staff Workload, and Enhanced Staff Satisfaction Using a Critical Path for Result Validation

Cited by 3 publications

References 27 publications

An Auto-Approval Approach for Laboratory Test Assessment

An Auto-Approval Approach for Laboratory Test Assessment

Automation in Clinical Laboratories: A Comprehensive Bibliography Review

Impact of Autoverification in the Hematology Laboratory: Experience with LimasVfy

Contact Info

Product

Resources

About