Fast prototyping of a local fuzzy search system for decision support and retraining of hospital staff during pandemic.
COVID-19
Decision support algorithm
Fuzzy search
Patient-like-mine
Prototyping
Journal
Health information science and systems
ISSN: 2047-2501
Titre abrégé: Health Inf Sci Syst
Pays: England
ID NLM: 101638060
Informations de publication
Date de publication:
Dec 2021
Dec 2021
Historique:
received:
07
10
2020
accepted:
16
04
2021
entrez:
14
5
2021
pubmed:
15
5
2021
medline:
15
5
2021
Statut:
epublish
Résumé
The COVID-19 pandemic showed an urgent need for decision support systems to help doctors at a time of stress and uncertainty. However, significant differences in hospital conditions, as well as skepticism of doctors about machine learning algorithms, limit their introduction into clinical practice. Our goal was to test and apply the principle of "patient-like-mine" decision support in rapidly changing conditions of a pandemic. In the developed system we implemented a fuzzy search that allows a doctor to compare their medical case with similar cases recorded in their medical center since the beginning of the pandemic. Various distance metrics were tried for obtaining clinically relevant search results. With the use of R programming language, we designed the first version of the system in approximately a week. A set of features for the comparison of the cases was selected with the use of random forest algorithm implemented in Caret. Shiny package was chosen for the design of GUI. The deployed tool allowed doctors to quickly estimate the current conditions of their patients by means of studying the most similar previous cases stored in the local health information system. The extensive testing of the system during the first wave of COVID-19 showed that this approach helps not only to draw a conclusion about the optimal treatment tactics and to train medical staff in real-time but also to optimize patients' individual testing plans. This project points to the possibility of rapid prototyping and effective usage of "patient-like-mine" search systems at the time of a pandemic caused by a poorly known pathogen.
Identifiants
pubmed: 33986947
doi: 10.1007/s13755-021-00150-y
pii: 150
pmc: PMC8112214
doi:
Types de publication
Journal Article
Langues
eng
Pagination
21Informations de copyright
© The Author(s) 2021.
Déclaration de conflit d'intérêts
Conflict of interestThe authors declare that they have no conflict of interest.
Références
Appl Clin Inform. 2020 May;11(3):452-459
pubmed: 32610350
Big Data. 2019 Dec;7(4):221-248
pubmed: 31411491
N Engl J Med. 2020 Aug 6;383(6):517-525
pubmed: 32492293
Health Aff (Millwood). 2014 Jul;33(7):1229-35
pubmed: 25006150
NPJ Digit Med. 2019 Mar 19;2:16
pubmed: 31304364
Infect Dis Model. 2020;5:282-292
pubmed: 32292868
BMJ. 2020 Apr 7;369:m1328
pubmed: 32265220
Transp Res E Logist Transp Rev. 2020 Jun;138:101967
pubmed: 32382249
Clin Infect Dis. 2020 Sep 12;71(6):1393-1399
pubmed: 32271369
N Engl J Med. 2020 Jun 18;382(25):2411-2418
pubmed: 32379955
Appl Clin Inform. 2020 Mar;11(2):265-275
pubmed: 32268390
Lancet. 2020 Jun 13;395(10240):1820
pubmed: 32511943
Brief Bioinform. 2021 Mar 22;22(2):642-663
pubmed: 33147627
N Engl J Med. 2021 Feb 25;384(8):693-704
pubmed: 32678530
Nature. 2020 Jun 12;:
pubmed: 34117465
J Healthc Eng. 2020 Nov 23;2020:8889412
pubmed: 33299538
NPJ Digit Med. 2020 Feb 6;3:17
pubmed: 32047862
Sci Total Environ. 2020 Jul 20;727:138394
pubmed: 32334207
BMC Med Res Methodol. 2020 Sep 21;20(1):235
pubmed: 32958001
N Engl J Med. 2020 Jun 18;382(25):e102
pubmed: 32356626
Expert Rev Respir Med. 2020 Dec;14(12):1257-1260
pubmed: 32701376
J Med Internet Res. 2020 Jun 29;22(6):e19786
pubmed: 32540845
Chest. 2020 Oct;158(4):1364-1375
pubmed: 32533957
PLoS One. 2019 Sep 24;14(9):e0221459
pubmed: 31550255
JMIR Med Inform. 2014 Nov 04;2(2):e30
pubmed: 25601050
Eur Respir J. 2020 Aug 20;56(2):
pubmed: 32616597
Chin Med J (Engl). 2016 Mar 20;129(6):731-8
pubmed: 26960378