FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W49552497> ?p ?o ?g. }

• W49552497 abstract "We present novel machine learning and data mining methods that make real-world learning systems more efficient. We focus on the domain of clinical informatics, an archetypical example of a field overwhelmed with information. Due to properties inherent to clinical informatics tasks – and indeed, to many tasks that require specialized domain knowledge – 'off-the-shelf' machine learning technologies generally perform poorly in this domain.If machine learning is to be successful in clinical science, novel methods must be developed to: mitigate the effects of class imbalance during model induction; exploit the wealth of domain knowledge highly skilled domain experts bring to the task; and to induce better models with less effort (fewer labels). We present new machine learning methods that address each of these issues, and demonstrate their efficacy in the task of abstract screening. In particular, we develop new theoretical perspectives on class imbalance, novel methods for exploiting dual supervision (i.e., labels on both instances and features), and new active learning techniques that address issues inherent to real-world applications (e.g., exploiting multiple experts in tandem). Each of these contributions aims to squeeze better classification performance out of fewer labels, thereby making better use of domain experts' time and expertise.The immediate aim in this work is to reduce the workload involved in conducting systematic reviews, and to this end we demonstrate that the developed methods can reduce reviewer workload by more than half, without sacrificing the comprehensiveness of reviews (i.e., without missing any relevant published evidence). But this is only an exemplary task; the approaches presented here have wider application to many real-world learning problems, i.e., those that require specialized expertise, exhibit class imbalance (and asymmetric costs) and for which limited human resources are available. We show that the methods we have developed bring substantial improvements over previously existing machine learning approaches in terms of inducing better models with less effort." @default.
• W49552497 created "2016-06-24" @default.
• W49552497 creator A5036790226 @default.
• W49552497 creator A5045379675 @default.
• W49552497 date "2012-01-01" @default.
• W49552497 modified "2023-09-26" @default.
• W49552497 title "Machine learning in health informatics: making better use of domain experts" @default.
• W49552497 cites W123339444 @default.
• W49552497 cites W1492818624 @default.
• W49552497 cites W1522553155 @default.
• W49552497 cites W1528361845 @default.
• W49552497 cites W1528905581 @default.
• W49552497 cites W1531719573 @default.
• W49552497 cites W1532325895 @default.
• W49552497 cites W1532734293 @default.
• W49552497 cites W1533970595 @default.
• W49552497 cites W1540371141 @default.
• W49552497 cites W1551909886 @default.
• W49552497 cites W1592853229 @default.
• W49552497 cites W1599263113 @default.
• W49552497 cites W1605491412 @default.
• W49552497 cites W1618905105 @default.
• W49552497 cites W1664950380 @default.
• W49552497 cites W167016754 @default.
• W49552497 cites W168362576 @default.
• W49552497 cites W169052826 @default.
• W49552497 cites W1841840321 @default.
• W49552497 cites W1941659294 @default.
• W49552497 cites W1965895350 @default.
• W49552497 cites W1989445634 @default.
• W49552497 cites W1995945562 @default.
• W49552497 cites W2008056655 @default.
• W49552497 cites W2010135967 @default.
• W49552497 cites W2012942264 @default.
• W49552497 cites W2017079501 @default.
• W49552497 cites W2018770010 @default.
• W49552497 cites W2022775778 @default.
• W49552497 cites W2037771830 @default.
• W49552497 cites W2040010062 @default.
• W49552497 cites W2040260156 @default.
• W49552497 cites W2040870580 @default.
• W49552497 cites W2042932437 @default.
• W49552497 cites W2043566294 @default.
• W49552497 cites W2045030989 @default.
• W49552497 cites W2047132989 @default.
• W49552497 cites W2048679005 @default.
• W49552497 cites W2053920233 @default.
• W49552497 cites W2056983531 @default.
• W49552497 cites W2062866389 @default.
• W49552497 cites W2065267227 @default.
• W49552497 cites W2067760738 @default.
• W49552497 cites W2070808135 @default.
• W49552497 cites W2078129874 @default.
• W49552497 cites W2080021732 @default.
• W49552497 cites W2085989833 @default.
• W49552497 cites W2097726431 @default.
• W49552497 cites W2098824882 @default.
• W49552497 cites W2100053037 @default.
• W49552497 cites W2102417402 @default.
• W49552497 cites W2105897558 @default.
• W49552497 cites W2107328434 @default.
• W49552497 cites W2107961375 @default.
• W49552497 cites W2109378394 @default.
• W49552497 cites W2114524997 @default.
• W49552497 cites W2118978333 @default.
• W49552497 cites W2119168155 @default.
• W49552497 cites W2119821739 @default.
• W49552497 cites W2120354757 @default.
• W49552497 cites W2122589015 @default.
• W49552497 cites W2123108597 @default.
• W49552497 cites W2125327503 @default.
• W49552497 cites W2125943921 @default.
• W49552497 cites W2126502509 @default.
• W49552497 cites W2129018774 @default.
• W49552497 cites W2129861887 @default.
• W49552497 cites W2130834086 @default.
• W49552497 cites W2131123062 @default.
• W49552497 cites W2131427446 @default.
• W49552497 cites W2132791018 @default.
• W49552497 cites W2133990480 @default.
• W49552497 cites W2134134392 @default.
• W49552497 cites W2135266614 @default.
• W49552497 cites W2135892731 @default.
• W49552497 cites W2136903812 @default.
• W49552497 cites W2138273245 @default.
• W49552497 cites W2139709458 @default.
• W49552497 cites W2140679654 @default.
• W49552497 cites W2142518823 @default.
• W49552497 cites W2146006411 @default.
• W49552497 cites W2147594372 @default.
• W49552497 cites W2149298154 @default.
• W49552497 cites W2149308034 @default.
• W49552497 cites W2149344544 @default.
• W49552497 cites W2149684865 @default.
• W49552497 cites W2153635508 @default.
• W49552497 cites W2154103141 @default.
• W49552497 cites W2162096170 @default.
• W49552497 cites W2163302275 @default.
• W49552497 cites W2165951927 @default.
• W49552497 cites W2166353350 @default.

• next