Optimized Scoring Systems: Toward Trust in Machine Learning for Healthcare and Criminal Justice

被引：57

作者：

Rudin, Cynthia ^{[1
,2
,3
]}

Ustun, Berk ^{[4
]}

机构：

[1] Duke Univ, Dept Comp Sci, Durham, NC 27708 USA

[2] Duke Univ, Dept Elect & Comp Engn, Durham, NC 27708 USA

[3] Duke Univ, Dept Stat Sci, Durham, NC 27708 USA

[4] Harvard Univ, Harvard John A Paulson Sch Engn & Appl Sci, Ctr Res Computat Soc, Cambridge, MA 02138 USA

来源：

INTERFACES | 2018年 / 48卷 / 05期

基金：

美国国家科学基金会;

关键词：

machine learning; sparse linear models; socring systems; trust; transparency; Interpretability; healthcare; criminal justice; recidivism; CLASSIFICATION MODELS; HOSPITAL MORTALITY; ACUTE PHYSIOLOGY; RISK PREDICTION; CHEST-PAIN; APACHE; RECIDIVISM; VALIDATION; STROKE; RULES;

D O I：

10.1287/inte.2018.0957

中图分类号：

C93 [管理学];

学科分类号：

12 ; 1201 ; 1202 ; 120202 ;

摘要：

Questions of trust in machine-learning models are becoming increasingly important as these tools are starting to be used widely for high-stakes decisions in medicine and criminal justice. Transparency of models is a key aspect affecting trust. This paper reveals that there is new technology to build transparent machine-learning models that are often as accurate as black-box machine-learning models. These methods have already had an impact in medicine and criminal justice. This work calls into question the overall need for black-box models in these applications.

引用

页码：449 / 466

页数：18

共 50 条

[31] Toward Efficient Online Scheduling for Distributed Machine Learning Systems
Yu, Menglu
Liu, Jia
Wu, Chuan
Ji, Bo
Bentley, Elizabeth S.
IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING, 2022, 9 (04): : 1951 - 1969
[32] Machine Learning: A Path Toward Optimized Smell Tests for Screening COVID-19
Doty, Richard L.
CHEMICAL SENSES, 2021, 46
[33] Local Justice and Machine Learning: Modeling and Inferring Dynamic Ethical Preferences toward Allocations
Chen, Violet
Williams, Joshua
Leben, Derek
Heidari, Hoda
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 5, 2023, : 5956 - 5964
[34] The needs of people with mild learning disabilities within the Scottish criminal justice system: a qualitative study of healthcare perspectives
Mediseni, Fellex
Brown, Michael
JOURNAL OF INTELLECTUAL DISABILITIES AND OFFENDING BEHAVIOUR, 2015, 6 (3-4) : 175 - 186
[35] An efficient disease prediction framework based on optimized machine learning models for a smart healthcare application
Jiao, Na
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (17) : 50825 - 50848
[36] An efficient disease prediction framework based on optimized machine learning models for a smart healthcare application
Na Jiao
Multimedia Tools and Applications, 2024, 83 : 50825 - 50848
[37] Machine learning-based intrusion detection for SCADA systems in healthcare
Öztürk, Tolgahan
Turgut, Zeynep
Akgün, Gökçe
Köse, Cemal
Network Modeling Analysis in Health Informatics and Bioinformatics, 2022, 11 (01)
[38] Machine Learning-based Fall Detection in Geriatric Healthcare Systems
Ramachandra, Anita
Adarsh, R.
Pahwa, Piyush
Anupama, K. R.
2018 IEEE INTERNATIONAL CONFERENCE ON ADVANCED NETWORKS AND TELECOMMUNICATIONS SYSTEMS (ANTS), 2018,
[39] Machine learning-based intrusion detection for SCADA systems in healthcare
Ozturk, Tolgahan
Turgut, Zeynep
Akgun, Gokce
Kose, Cemal
NETWORK MODELING AND ANALYSIS IN HEALTH INFORMATICS AND BIOINFORMATICS, 2022, 11 (01):
[40] Adversarial Attacks to Machine Learning-Based Smart Healthcare Systems
Newaz, A. K. M. Iqtidar
Haque, Nur Imtiazul
Sikder, Amit Kumar
Rahman, Mohammad Ashiqur
Uluagac, A. Selcuk
2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2020,

← 1 2 3 4 5 →