A machine learning approach to disaster-related trauma and subsequent functional limitations

Machine Learning


In addition to social and economic losses, large-scale natural disasters often negatively impact the mental and cognitive health of survivors.

To Dr. Tystere Matondo BantidiTemblor Science Writing Extern (@Thysterebantidi)

Quote: Bantidi, T., 2023, Machine Learning Approaches to Disaster-Related Trauma and Subsequent Functional Limitations, Temblor, http://doi.org/10.32858/temblor.311

Every year, the global community experiences severe damage from various natural disasters such as earthquakes, tsunamis, floods and tropical cyclones. In addition to physical damage to people and property, survivors can suffer mental and cognitive health problems caused by the shock of losing loved ones and sudden disruptions in homes and communities. Often the poorest and most marginalized members of society experience the most adverse effects.

Decision makers tasked with allocating resources for recovery after a natural disaster often prioritize immediate damage. That’s not wrong, but it leaves out the people most likely to struggle in the long run. Therefore, by investigating how these traumatic experiences affect survivors and linking those effects to factors such as age, marital status, education level, and income, we can better understand how disasters affect the lives of vulnerable people. Assistant Koichiro Shiba said it could provide insight into its relationship with health. Professor of Epidemiology, Boston University and lead author of a new study published in the American Journal of Epidemiology.

In this study, Shiba and his colleagues describe the adverse health effects of disaster-related trauma in the aftermath of the 2011 Tohoku earthquake and tsunami off the Pacific coast of Honshu. This effort will impact post-disaster recovery everywhere.

earthquake

The magnitude 9.0 Tohoku-Oki earthquake, also known as the Great East Japan Earthquake, occurred along the Japan Trench where the Pacific plate subducts beneath the Okhotsk plate. In such subduction zones, where one tectonic plate slides under another, the descending slab can get stuck and stress can build up. When some or all of that stress is suddenly released, an earthquake occurs.

The Tohoku earthquake also triggered a massive tsunami, destroyed the Fukushima Daiichi nuclear power plant, and made parts of the area uninhabitable for nearly a decade due to radioactive contamination. This triple disaster of earthquake, tsunami and nuclear meltdown killed at least 19,729 people, including thousands of unrecovered victims. Over 121,000 homes were destroyed, and he damaged nearly a million more. More than 10 years later, many people are still living in temporary housing.

This map shows the strength of the 2011 off the Pacific coast of Tohoku earthquake and the height of the tsunami. Dark red represents higher intensity. All things being equal, stronger shaking can cause more damage. Credit: Hyogo Framework for Action 2005-2015: Building the Resilience of States and Communities to Disasters, 2014, International Research Institute of Disaster Science, Tohoku University.

lose your home, lose your health

“Mental health” relates to psychological and emotional health and includes conditions such as anxiety and depression. “Cognitive health” relates to brain functioning and includes memory, language, problem-solving and decision-making. “Functional health” relates to the ability to perform daily tasks such as bathing, dressing and eating. These three health types are interrelated, meaning that problems in one area can affect others.

For example, people with mental health conditions, such as schizophrenia, may have difficulty making decisions due to cognitive decline, resulting in difficulty performing tasks of daily living and impaired functioning. It can affect your health. Cognitive health problems, such as dementia, can lead to behavioral changes that can affect both mental and functional health, again making it difficult for individuals to perform tasks of daily living. becomes difficult. Functional health problems such as chronic pain can also lead to depression and anxiety, affecting mental health, which in turn can affect cognitive abilities such as concentration and memory. .

Many studies have identified how individuals respond to trauma. These studies yielded two main results. First, some people who experience trauma do not develop mental health problems. They are called elastic. Second, research shows that there is a correlation between the degree of trauma experienced by someone, called trauma exposure, and their mental and cognitive health.

Cognitive health research tends to show a correlation between trauma exposure and functional health. The more trauma a person experiences, the more likely that person is to have more problems trying to live a normal life, and their functional health is affected. As a result of earthquakes and tsunamis, survivors are exposed to trauma, and trauma can manifest as mental, cognitive, or functional health problems, but they are interconnected and impactful of their relationships. Untangling is not easy. Shiba’s new research explores the relationship between the trauma inflicted by these disasters and functional health, as well as the factors that exacerbate trauma exposure, including mental and cognitive health.

To this end, Shiba and his collaborators collected 1,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,0,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000,000),000))]or Japanese) colleague]We used data before and after the earthquake. The city was part of a nationwide cohort study of older adults in Japan called the Japan Gerontological Evaluation Study (JAGES).

In Iwanuma, the JAGES survey began in 2010, just seven months before the disaster struck. During his five-and-a-half years after the earthquake, JAGES, in his 2013 and 2016, next he studied disaster survival to measure an individual’s functional limits using three different indicators. I surveyed people. ) ; Activities of daily living (eg, ability to accomplish basic daily activities such as walking and bathing). Instrumental activities of daily living (such as using public transport).

The 2011 Tohoku earthquake and subsequent tsunami devastated coastal cities in this region. Credit: NOAA/Katherine Muller (International Federation of Red Cross).

machine learning techniques

Machine learning approaches use algorithms that enable scientists to discover hidden insights within data. Algorithms then “learn” from these insights and make predictions. Shiba’s team used a machine learning approach trained on 55 pre-disaster features from the baseline of the JAGES survey conducted in 2010. This includes demographic characteristics, measures of socioeconomic status, health status, psychosocial factors and behavioral factors.

The researchers compared the pre-disaster demographic characteristics of the surveyed post-disaster homeless elderly populations to estimate the average impact of housing loss on functional health. They investigated whether some of the demographic characteristics of homeless people correlated with their ability to carry out their daily lives. So the answer is yes.

Based on their analysis, the researchers estimated that people who lost their homes had increased functional limitations. Furthermore, those who experienced these limitations tended to be of lower socioeconomic background. Those who had symptoms of clinical depression before the disaster were also more likely to experience functional limitations after the disaster.

The researchers also found that more vulnerable people were more likely to be older, unemployed single men who lived alone and had relatively low levels of education. Members of this vulnerable group also had underlying health problems, including increased symptoms of depression and worsening self-rated health. Nevertheless, income was not always a good predictor of vulnerability. People with higher incomes but lower education levels also appeared to be more vulnerable to disasters.

These results provide new insights that may have been overlooked by previous studies that link high income alone to disaster resilience. New research reveals more complex relationships arising from interactions between multiple traits, such as education and gender. However, the mechanism of such complex heterogeneity remains unclear, and further research is needed, says Shiba.

“Temporary” housing for survivors of the 2011 Tohoku earthquake and subsequent tsunami in Onagawa (some people still live in such housing more than a decade after the disaster). Credit: Forgemind ArchiMedia, CC BY 2.0

Support for the elderly

Older people are especially prone to post-traumatic stress disorder and depression because of the confusion of where they live. “This fact alone explains why we should be concerned about their physical, psychological or mental health after a natural disaster,” said one of the researchers involved in the study. says Emmanuel Kagning-Zinda, a postdoctoral fellow at the Massachusetts Institute of Technology’s Center for Biomedical Innovation.

This new study not only highlights variables that may explain post-disaster resilience and vulnerability of older adults, but also provides a model that can help predict which individuals are at higher risk of experiencing adverse effects after a natural disaster. It also offers, Zinda said. Such information could help decision-makers allocate resources more equitably throughout the different stages of a disaster: pre-disaster mitigation and preparedness, during-disaster response, and post-disaster recovery. he says.

Natural disasters like the Tohoku earthquake and tsunami can have long-lasting effects on survivors. Nevertheless, policymakers can use the new findings to take measures that prioritize the well-being and safety of both individuals and communities, Shiba says. Prioritizing resource allocation to those most likely to struggle most with long-term recovery will contribute to more targeted post-disaster public health interventions, thereby preserving the functional health of survivors. can do.

References

Kazuya Shiba, Akira Dowd, Hiroshi Hikichi, Akira Yazawa, Jun Aida, Kazu Kondo, and Hajime Kawachi (2022). Uncovering heterogeneous associations between disaster-related trauma and subsequent functional limitations: a machine learning approach. American Journal of Epidemiology, 192(2), 217-229.

Copyright

Text © 2023 Temblor. CC BY-NC-ND 4.0

We publish articles, maps, and other works created by Temblor under a Creative Commons Attribution – Noncommercial.
NoDerivatives 4.0 International License (CC BY-NC-ND 4.0).

Please see our reissue guidelines for more information or contact us at news@temblor.net with any questions.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *