Supervised patient similarity measure of heterogeneous patient records

By Jimeng Sun, Fei Wang, Jianying Hu, Shahram Edabollahi. 2012

159 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Epidemiology, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jimeng Sun
2. Fei Wang
3. Edward Choi
4. Huamin Qu
5. Yao Ming
6. Liu Ren
7. Panpan Xu
8. Walter F. Stewart

In Epidemiology

1. Fei Wang
2. Jimeng Sun
3. Robert Sorrentino
4. Ping Zhang
5. Edward Choi
6. Jianying Hu
7. Walter F. Stewart
8. Anna Goldenberg

In Management Science and Operations Research

1. Fei Wang
2. Jimeng Sun
3. Ben Shneiderman
4. Mohammad Taha Bahadori
5. Edward Choi
6. Shalmali Joshi
7. Walter F. Stewart
8. Anna Goldenberg

Citations in the corpus

• RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism (2016, background): “raditional models [6]: 1) identifying a set of rules (e.g. via decision trees [24]), 2) case-based reasoning by finding similar patients (e.g. via k-nearest neighbors [16] and distance metric learning [33]), and 3) identifying a list of risk factors (e.g. via LASSO coefficients [15]). While interpreta”
• Interpretable and Steerable Sequence Learning via Prototypes (2019, methodology): “Different from nearest neighbor classifiers used in typical case-based reasoning systems [30, 32], in our approach only a few selected prototypes are memorized, simplified and used for reasoning.”
• Temporal Event Sequence Simplification (2013, methodology): “It combined the list-based display of its predecessor, LifeLines2 [28], with an aggregated display that summarized the entire dataset in a single view.”
• What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use (2019, background): “Clinicians view this as finding similar patients (Sun et al., 2012; Zhu et al., 2016; Sharafoddini et al., 2017) and believe that this kind of explanation can be only helpful in specific applications.”
• Towards Personalized Medicine: Leveraging Patient Similarity and Drug Similarity Analytics (2014, methodology): “With the right patient similarity in place, patient similarity analytics have been used in the target patient retrieval 14 , medical prognosis 15, 16 , risk stratification 17, 18 , and clinical pathway analysis 19 tasks.”