scholarly journals Establishing and validating of an laboratory information system‐based auto‐verification system for biochemical test results in cancer patients

2019 ◽  
Vol 33 (5) ◽  
Author(s):  
Cuie Yan ◽  
Yujuan Zhang ◽  
Jia Li ◽  
Jia Gao ◽  
Chanjuan Cui ◽  
...  
2021 ◽  
Author(s):  
Di Jin ◽  
Qing Wang ◽  
Dezhi Peng ◽  
Jiajia Wang ◽  
Yating Cheng ◽  
...  

Abstract BackgroundValidation of the autoverification function is the most critical step to confirm its effectiveness before use. It is crucial to verify whether the programmed algorithm follows the expected logic and produces the expected results. In recent years, this process has always been centered on the assessment of human-machine consistency and mostly takes the form of manual recording, which is a time-consuming activity with inherent subjectivity and arbitrariness, and cannot guarantee a comprehensive, timely and continuous effectiveness evaluation of the autoverification function. To overcome these inherent limitations, we independently developed and implemented a laboratory information system (LIS)-based validation system for autoverification.MethodsWe developed a correctness verification and integrity validation method (hereinafter referred to as the "new method") in the form of a human-machine dialogue. The system records the personnel’s review steps and determines if the human-machine review results are consistent. If they are inconsistent, the laboratory personnel analyze the reasons for the inconsistency according to the system prompts, add to or modify the rules, reverify, and finally improve the accuracy of autoverification.ResultsThe validation system was successfully established and implemented. For a dataset consisting of 833 rules for 30 assays, 782 rules (93.87%) were successfully verified in the correctness verification phase, and 51 rules were deleted due to execution errors. In the integrity validation phase, 24 projects were easily verified, while the other 6 projects still required the addition of new rules or changes to the rule settings. From setting the rules to the automated reportion, the time difference between manual validation and the new method, was statistically significant (χ2=11.06, p=0.0009), with the new method greatly reducing validation time. Since 2017, the new method has been used in 32 laboratories, and 15.8 million reports have been automatically reviewed and issued without a single clinical complaint.ConclusionTo the best of our knowledge, this is the first report to realize autoverification validation in the form of a human-machine interaction.The new method can effectively control the risks of autoverification, shorten time consumption, and improve the efficiency of laboratory verification.


2020 ◽  
Author(s):  
Philip Boakye

The acceptance of electronic laboratory information system (LIS) is gradually increasing in developing countries. However, the issue of time effectiveness due to computerization is less clear as there is fewer accessible information. One of the key issues for laboratorians is their indecision with LISs’ would-be effect of time on their work. A polyclinic in Ghana was in the process of implementing electronic LIS. Several of the laboratorians did not have knowledge and skill in computing and there were disagreeing views on the time effectiveness of the LIS after implementation. The management of the polyclinic laboratory was concerned to assess time advantageousness of recording data when using the electronic LIS compared with paper-based LIS. <div><br></div><div>Five randomly selected laboratorians were provided two sheets of paper with tables to document the time they spent for both paper-based and electronic LIS. Data were collected for a total of 230 records,115 electronic LIS and 115 paper-based LIS. The t-test (mean-comparison test) was computed to compare the means of both electronic and paperbased LIS times. </div><div><br></div><div>There was a statistical significant difference in the time spent between electronic and paper-based LIS. The time spent between paper-based and electronic LIS was 0.41 minutes (95% CI 0.15 to 0.66) longer than in electronic LIS. </div><div><br></div><div>LIS can be adopted in polyclinics without having significant negative impact on time spent between electronic and paper-based LIS. More time–motion studies that include laboratorians are however necessary in order to get a more complete picture of time spent between electronic and paper-based LIS. </div>


2016 ◽  
Vol 100 (5) ◽  
pp. 437-440 ◽  
Author(s):  
X Chu ◽  
K Bleasby ◽  
GH Chan ◽  
I Nunes ◽  
R Evers

2010 ◽  
Vol 134 (8) ◽  
pp. 1152-1159 ◽  
Author(s):  
Lewis A. Hassell ◽  
Anil V. Parwani ◽  
Lawrence Weiss ◽  
Michael A. Jones ◽  
Jay Ye

Abstract Context.—The site-specific cancer checklists developed by the College of American Pathologists have the potential to improve the quality of data derived from pathology reports and incorporated into cancer registry databases and are now mandated report elements by various accrediting bodies. A pilot project, funded by the Centers for Disease Control National Project for Cancer Registries in 2004, brought 4 pathology services in 3 states, with differing baseline implementations of the checklists, the opportunity to partner with their state National Project for Cancer Registry and their laboratory information system vendors to evaluate the feasibility of using electronically encoded College of American Pathologists cancer checklists for melanoma and tumors of the breast and prostate. Objectives.—To identify existing and potential barriers to adoption of electronically encoded checklists and to also identify unique benefits not associated with text-only uses of the checklists. Design.—Participants mapped an implementation process from their current state to an electronic checklist–capable state. For a sample of cases of melanoma, prostate, and breast cancers, the checklist elements were captured and transmitted to the registry using Health Level 7 (version 2.3.1). Process assessments with adoption of electronic checklists were conducted to assess pathologist effect and other potential barriers. An evaluation of the utility and usefulness of electronic checklists was performed after the project. Results.—All 4 laboratories successfully performed the capture of individual data elements from the College of American Pathologists checklist into a discrete format suitable for electronic transmission. The effect on pathologist performance and laboratory workflow was neutral. Points of resistance were identified in the checklists and in individual users. Specific challenges in individual laboratories varied according to the personnel and the baseline system in use. Clinical responses to implemented changes were generally positive. Analysis of the postproject experiences of the laboratories showed expansion of use and additional utility in some, but not all, laboratories. Conclusions.—Pathology laboratory adoption of the College of American Pathologists cancer checklists in an electronic format suited to direct transmission to cancer registries poses business case, information technology, and human resource challenges. Laboratory information system vendor readiness to upgrade systems to facilitate this process helps to reduce some of these challenges. Personalities and preferences in practices may yet pose barriers to widespread adoption.


2018 ◽  
Vol 43 (1) ◽  
pp. 98-100
Author(s):  
Saadet Celik ◽  
Tuncay Seyrekel ◽  
Medeni Arpa

AbstractObjective:Sample rejection is an important step in the laboratory related with the patient safety. Periodical analysis of rejected samples is necessary to define the causes of rejection and follow-up the requirements for staff training. In this study, we aimed to put forth the efficiency of trainings by analyzing the amount of rejected samples in Yozgat State Hospital.Materials and methods:Taken from laboratory information system (LIS), rejected sample statistics related to 8 month-data before training was compared with 8-month data after training between 07.2015 and 10.2016 are examined. These datas were compared in itself and to each other. All statistical analyses were performed using the SPSS (V15).Results:Before training, the average number of patients for the analysis included months was 34,733 [standard deviation (SD)±4031], the number of rejected samples was 397.7 (SD±85.3) and the average rejection percentage was 1.13 (min-max: 1–1.29). The average number of patients for the after training months was 39,426 (SD±4779), the number of rejected samples was 343.2 (SD±57.7) and the average rejection percentage was 0.87 (min-max: 0.62–0.98), Rejected sample rates were significantly lower interms of statistics in the after-training group (p=0.0001).Conclusion:Staff training takes a very important place preventing these mistakes. As it can be seen in our study, training helps decreasing rejection rates. It is suggested to schedule more trainings in order to decrease the rates to lower degrees.


Sign in / Sign up

Export Citation Format

Share Document