Select language Bahasa Indonesia Português (Brasil) Português (Portugal) Welcome to My Research! You may have access to the free features available through My Research. You can save searches, save documents, create alerts and more. Please log in through your library or institution to check if you have access. Translate this article into 20 different languages! If you log in through your library or institution you might have access to this article in multiple languages. Get access to 20+ different citations styles Styles include MLA, APA, Chicago and many more. This feature may be available for free if you log in through your library or institution. Looking for a PDF of this document? You may have access to it for free by logging in through your library or institution. Want to save this document?

You may have access to different export options including Google Drive and Microsoft OneDrive and citation management tools like EndNote Fusion and EasyBib. Try logging in through your library or institution to get access to these tools. Preview Available Scholarly Journal No items selected Please select one or more items. Select results items first to use the cite, email, save, and export options You might have access to the full article... Try and log in through your institution to see if they have access to the full text. Workplace violence and harassment toward healthcare providers is a major challenge for healthcare organizations around the world 1 . Evidence suggests that up to 38% of healthcare providers suffer violence in the workplace at some point in their careers, and incidents of physical intimidation, threats, verbal abuse, and sexual harassment are also common 2 . Research also indicates that the frequency of violent events and harassment of healthcare providers has continued to increase since the COVID-19 pandemic 3, 4–5 , exacerbating provider burnout and leading to increased stress, staff turnover, absenteeism, and reduced job satisfaction and taking an overall toll on mental and physical health 1 . For medical inpatients, psychiatrists may be consulted to diagnose, treat, or de-escalate when staff perceive possible risk, but staff-initiated requests for consultation are often too late or never begun. At the same time, recent advances in machine learning and natural language processing (NLP) have demonstrated significant potential in training and fine-tuning sophisticated screening models capable of matching or even surpassing the capabilities of human experts 6, 7, 8–9 , and often doing so automatically, far faster, and at greater scale. We hypothesized that NLP models trained on corpora of clinical notes preceding past violent events could be utilized to prospectively determine patients and staff at risk of violence, enabling intervention and prevention. Predicting violence against healthcare workers is challenging for a number of reasons. Actuarial models of suicidal or recidivistic criminal violence are notoriously poor, lacking dynamic input. Real-time data allows for better violence prediction, but requires time for universal screening to capture dynamic risks and complex interplay among patients, wards, hospitals, and social factors. Patients’ histories, illnesses, perceptions, and behavioral symptoms clearly define risks, as captured in screening measures such as the ABRAT 10 . Violence is more likely against individual healthcare workers with less experience, who are themselves insecure 11 and anxious 12 , often in conditions of overwhelming traumatic stress. Violence is more prevalent in clinical environments where staff are too busy to respond to these acute needs 13 , reflecting institutional inequities and management decisions. The concentration of patients with a high static risk for violence in under-resourced clinical environments staffed by inexperienced and traumatized healthcare workers is a recipe for driving burnout... You have requested "on-the-fly" machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Show full disclaimer Neither ProQuest nor its licensors make any representations or warranties with respect to the translations. The translations are automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. PROQUEST AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the translations is subject to all use restrictions contained in your Electronic Products License Agreement and by using the translation functionality you agree to forgo any and all claims against ProQuest or its licensors for your use of the translation functionality and any output derived there from. Hide full disclaimer Suggested sources