0.25
0.5
0.75
1.25
1.5
1.75
2
Machine Learning in Health Informatics: Making Better use of Domain Experts
Published on Sep 27, 20136259 Views
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 overwhe
Related categories
Chapter list
Machine Learning in Health Informatics: Making Better use of Domain Experts00:00
Advancing Machine Learning Through its Application00:33
This Work, More Specifically01:45
Evidence-Based Medicine02:26
EBM: Systematic Reviews - 102:52
EBM: Systematic Reviews - 204:16
Abstract Screening - 104:20
Abstract Screening - 204:40
Abstract Screening - 304:54
In 2010 eleven systematic reviews were published every single day04:59
Semi-Automating Abstract Screening via Supervised Machine Learning05:35
Open Problems in Machine Learning - 106:10
Open Problems in Machine Learning - 207:31
Contributions - 107:42
Class Imbalance, Redux08:14
The Problem of Class Imbalance - 108:30
The Problem of Class Imbalance - 210:25
Bias11:26
Undersampling - 112:12
Undersampling - 212:31
Undersampling - 312:33
Undersampling - 412:35
When is Bias Likely? - 113:10
When is Bias Likely? - 214:07
Results (Updating Reviews) - 114:12
Results (Updating Reviews) - 214:30
The Trouble with Probability Estimates for Imbalanced Data14:42
Class Probability Estimates for Imbalanced Data - 116:51
Class Probability Estimates for Imbalanced Data - 217:15
Better Probability Estimates for Imbalanced Data17:30
Contributions - 218:49
The Constrained Weight Space Support Vector Machines (CW-SVM)19:03
Dual Supervision - 119:11
Dual Supervision - 219:39
Ranked Labeled Features19:50
Support Vector Machines - 120:26
Support Vector Machines - 220:43
Support Vector Machines - 320:59
The Constrained Weight Space SVM - 121:06
The Constrained Weight Space SVM - 221:12
Abstract Screening: Proton Beam21:45
Contributions - 322:45
Active Learning for Biomedical Citation Screening22:54
Supervised Learning23:03
Active Learning23:29
AL with Imbalanced Data23:58
Co-testing - 125:22
Co-testing - 226:12
Co-Testing with Labeled Terms26:19
Results (Micronutrients Review)27:13
Who Should Label What?27:47
Multiple Expert Active Learning28:09
MEAL: Key Questions29:33
Meta-Cognitive MEAL - 1 29:44
Meta-Cognitive MEAL - 230:36
Results (Micronutrients Review)31:32
Putting it All Together in a Deployed - System: abstrackr32:02
abstrackr - 132:23
abstrackr - 232:47
Conclusions32:56
Thanks33:40