ELIZA

return kwic search for findings out of >500 occurrences
299123 occurrences (No.77 in the rank) during 5 years in the PubMed. [cache]

167) The AI literature was narratively synthesized for each domain, and findings were considered in the context of incidence, cost, and preventability to make projections about the likelihood of AI improving safety.

--- ABSTRACT ---

PMID:33742085 DOI:10.1038/s41746-021-00423-6

2021 NPJ digital medicine

* The potential of artificial intelligence to improve patient safety: a scoping review.

- Artificial intelligence (AI) represents a valuable tool that could be used to improve the safety of care. Major adverse events in healthcare include: healthcare-associated infections, adverse drug events, venous thromboembolism, surgical complications, pressure ulcers, falls, decompensation, and diagnostic errors. The objective of this scoping review was to summarize the relevant literature and evaluate the potential of AI to improve patient safety in these eight harm domains. A structured search was used to query MEDLINE for relevant articles. The scoping review identified studies that described the application of AI for prediction, prevention, or early detection of adverse events in each of the harm domains. The AI literature was narratively synthesized for each domain, and findings were considered in the context of incidence, cost, and preventability to make projections about the likelihood of AI improving safety. Three-hundred and ninety-two studies were included in the scoping review. The literature provided numerous examples of how AI has been applied within each of the eight harm domains using various techniques. The most common novel data were collected using different types of sensing technologies: vital sign monitoring, wearables, pressure sensors, and computer vision. There are significant opportunities to leverage AI and novel data sources to reduce the frequency of harm across all domains. We expect AI to have the greatest impact in areas where current strategies are not effective, and integration and complex analysis of novel, unstructured data are necessary to make accurate predictions; this applies specifically to adverse drug events, decompensation, and diagnostic errors.

--- ABSTRACT END ---

[
right
kwic]

[frequency of next (right) word to findings]

(1)49 suggest	(13)9 support	(25)4 that	(37)2 encourage
(2)40 from	(14)9 will	(26)4 to	(38)2 illuminate
(3)36 of	(15)6 include	(27)4 we	(39)2 it
(4)33 null	(16)6 reveal	(28)3 also	(40)2 may
(5)25 were	(17)6 revealed	(29)3 further	(41)2 open
(6)24 and	(18)5 for	(30)3 presented	(42)2 suggested
(7)21 indicate	(19)5 regarding	(31)3 related	(43)2 the
(8)18 provide	(20)5 showed	(32)3 reported	(44)2 through
(9)17 are	(21)4 can	(33)3 with	(45)2 uncover
(10)15 in	(22)4 demonstrate	(34)2 by	(46)2 underline
(11)11 highlight	(23)4 have	(35)2 confirm
(12)9 on	(24)4 show	(36)2 emphasize

add keyword

--- WordNet output for findings --- =>研究(調査)結果 Overview of noun findings The noun findings has 1 sense (no senses from tagged texts) 1. findings -- (a collection of tools and other articles used by an artisan to make jewelry or clothing or shoes) Overview of noun finding The noun finding has 3 senses (first 3 from tagged texts) 1. (16) determination, finding -- (the act of determining the properties of something, usually by research or calculation; "the determination of molecular structures") 2. (3) finding -- (the decision of a court on issues of fact or law) 3. (1) finding -- (something that is found; "the findings in the gastrointestinal tract indicate that he died several hours after dinner"; "an area rich in archaeological findings") --- WordNet end ---