Real-Time Prediction of Medical Demand and Mental Health Status in Ukraine under Russian Invasion Using Tweet Analysis

Real-Time Prediction of Medical Demand and Mental Health Status in Ukraine under Russian Invasion Using Tweet Analysis

Susumu Fujii,^1,2 Yasuto Kunii,³ Sayuri Nonaka,¹ Yumiko Hamaie,³ Mizuki Hino,³ Shinichi Egawa,⁴ Shinichi Kuriyama⁵ and Hiroaki Tomita3,⁶

¹Disaster Medical Informatics Lab, International Research Institute of Disaster Science (IRIDeS), Tohoku University, Sendai, Miyagi, Japan
²Medical IT Center, Tohoku University Hospital, Sendai, Miyagi, Japan
³Department of Disaster Psychiatry, International Research Institute of Disaster Science (IRIDeS), Tohoku University, Sendai, Miyagi, Japan
⁴International Cooperation for Disaster Medicine Lab., International Research Institute of Disaster Science (IRIDeS), Tohoku University, Sendai, Miyagi, Japan
⁵Department of Disaster Public Health, International Research Institute of Disaster Science (IRIDeS), Tohoku University, Sendai, Miyagi, Japan
⁶Department of Psychiatry, Tohoku University Graduate School of Medicine, Sendai, Miyagi, Japan

Russia’s invasion of Ukraine (February 24, 2022) has begun and there are concerns about the impact on health care supply and mental health. This study analyzed tweets in the Ukrainian language to capture the medical needs and mental health conditions in wartime Ukraine by focusing on ostensibly relevant words. The number of tweets containing the keywords and their overall proportion was compared before and after the Russian invasion of Ukraine. The survey period was divided into four phases-the pre-2022 Russian invasion, acute phase (4 weeks), subacute phase (12 weeks), and the chronic phase (8 weeks) up to August 10, 2022. The analysis targeted tweets sent in Ukrainian. The tweets were screened using a set of six classes with 75 key groups and 303 Ukrainian (204 original Japanese) keywords. Overall, 98,526,440 tweets were analyzed, with a pre-invasion and post-onset average of 1,096,976 and 3,328,243 tweets/week (a 3.0-fold increase), respectively. Of these, 3,197,443 tweets contained the keywords, with a pre-invasion and invasion average of 26,241 and 114,640 tweets/week (a 4.4-fold increase), respectively. The post-onset phase witnessed a considerable increase in all classes-medical services, treatment, medical resources, medical situations, and special situations-but not in the symptom class. Keywords related to psychological distress and anxiety immediately increased during the acute phase; those related to depression and post-traumatic stress reactions continued increasing as the invasion persisted, which may have reflected the mental state of those impacted. Analyzing tweets is useful for predicting people’s real-time physical and mental health needs during wartime.

Keywords —— human-induced hazards; physical and mental health needs; social network system; twitter; Ukraine

===============================

Tohoku J. Exp. Med 2023, 259, 189-198.

Correspondence: Susumu Fujii, Department of Disaster Medical Informatics, Tohoku University School of Medicine, Bldg. 5, 2nd Floor, 2-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8575, Japan.

e-mail: sfujii@sfujii.net