Extracting Personal Medical Events for User Timeline Construction using Minimal Supervision

Abstract

In this paper, we describe a system for automatic construction of user disease progression timelines from their posts in online support groups using minimal supervision. In recent years, several online support groups have been established which has led to a huge increase in the amount of patient-authored text available. Creating systems which can automatically extract important medical events and create disease progression timelines for users from such text can help in patient health monitoring as well as studying links between medical events and users' participation in support groups. Prior work in this domain has used manually constructed keyword sets to detect medical events. In this work, our aim is to perform medical event detection using minimal supervision in order to develop a more general timeline construction system. Our system achieves an accuracy of 55.17%, which is 92% of the performance achieved by a supervised baseline system.

Identifying Language Features Associated With Needs of Ovarian Cancer Patients and Caregivers Using Social Media

“…Online health communities contain a wealth of information about users and their diseases. For example, users of cancer OHCs usually write about their cancer trajectory or stage information as well as their needs 46–48 . Although users do not identify their personal information, we can incorporate this information with need type to predict which needs can be met at the particular trajectory and/or cancer stage.…”

“…For example, users of cancer OHCs usually write about their cancer trajectory or stage information as well as their needs. [46][47][48] Although users do not identify their personal information, we can incorporate this information with need type to predict which needs can be met at the particular trajectory and/or cancer stage. Currently, we are expanding our model to incorporate detailed information about users from OHCs to detect their evolving needs and recommend online resources to meet those needs at the particular point of their cancer trajectory (grant number R01 LM013038).…”

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

“…Span-based and ontology-free extraction allows us to develop adaptable coding guidelines since event arguments and types are usually domain-specific or task-specific. This adaptability sets our work apart from other prior work on medical event extraction such as adverse drug event extraction (Nikfarjam et al, 2015;Cocos et al, 2017;Henry et al, 2020) and personal event extraction from online support groups (Wen et al, 2013;Naik et al, 2017), which focus on specific event types. Our guidelines draw heavily from the Thyme-TimeML guidelines (Styler IV et al, 2014) used by the Clinical TempEval challenges on event ordering in clinical notes (Bethard et al, 2015(Bethard et al, , 2016(Bethard et al, , 2017, 2 but also cover event extraction in a novel domain: doctor-patient conversations.…”

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

“…Span-based and ontology-free extraction allows us to develop adaptable coding guidelines since event arguments and types are usually domain-specific or task-specific. This adaptability sets our work apart from other prior work on medical event extraction such as adverse drug event extraction (Nikfarjam et al, 2015;Cocos et al, 2017;Henry et al, 2020) and personal event extraction from online support groups (Wen et al, 2013;Naik et al, 2017), which focus on specific event types. Our guidelines draw heavily from the Thyme-TimeML guidelines (Styler IV et al, 2014) used by the Clinical TempEval challenges on event ordering in clinical notes (Bethard et al, 2015(Bethard et al, , 2016(Bethard et al, , 2017, 1 but also cover event extraction in a novel domain: doctor-patient conversations.…”