Efficient and scalable early diagnostic methods for knee osteoarthritis are desired due to the disease’s prevalence. The current automatic methods for detecting osteoarthritis using plain radiographs struggle to identify the subjects with early-stage disease. Tibial spiking has been hypothesized as a feature of early knee osteoarthritis. Previous research has demonstrated an association between knee osteoarthritis and tibial spiking, but the connection to the early-stage disease has not been investigated. We study tibial spiking as a feature of early knee osteoarthritis. Additionally, we develop a deep learning based model for detecting tibial spiking from plain radiographs. We collected and graded 913 knee radiographs for tibial spiking. We conducted two experiments: experiments A and B. In experiment A, we compared the subjects with and without tibial spiking using Mann-Whitney U-test. Experiment B consisted of developing and validating an interpretative deep learning based method for predicting tibial spiking. The subjects with tibial spiking had more severe Kellgren-Lawrence grade, medial joint space narrowing, and osteophyte score in the lateral tibial compartment. The developed method achieved an accuracy of 0.869. We find tibial spiking a promising feature in knee osteoarthritis diagnosis. Furthermore, the detection can be automatized.

The news media plays a vital role in influencing public perceptions about topics, issues and crises. They also act as important intermediaries between organizations and public, enabling organizations to shape how people think about crisis topics and actors. Monitoring news coverage and assessing the news media's agenda‐setting role in a crisis can help organizations respond more effectively to emerging situations. When crises are prolonged and affect many countries, media analysis can become a tedious task for crisis managers. This study demonstrates how natural language processing (NLP) methods can be utilized in news media analysis of crisis situations, such as an extended cross‐national pandemic. Specifically, it demonstrates the possibilities of using NLP to identify and compare the salience of diverse crisis topics and how the media treat these topics and crisis actors (first‐ and second‐level agenda‐setting) across countries, news outlets, and time. The COVID‐19 pandemic serves as an illustrative case study to showcase the application of NLP techniques to provide insights into public perceptions of a major health crisis shaped by the news media in two Nordic countries (Finland and Sweden). Findings show the suitability of NLP methods to detect nuanced differences in news media coverage and offer relevant knowledge of how public perceptions and responsibility attribution fluctuate across time and countries.