Tiếp theoHướng dẫn tiếp theo
Dự đoán tái nhập viện AI
ngành công nghiệp
HƯỚNG DẪN ngành
AI fall risk prediction uses electronic health record data, and sometimes in-room video, to estimate which hospital patients are likely to fall and alert staff early.
Nghe hướng dẫn nàyAI thuật lại · ~3 min
It aims to improve on periodic bedside scores like the Morse Fall Scale. Falls cause injuries, longer stays and costs hospitals cannot recover, but an alert only helps if nurses can act on it without drowning in alarms.
The Morse Fall Scale, published by Janice Morse in 1989, scores six items: history of falling, secondary diagnosis, ambulatory aid, IV or saline lock, gait, and mental status. Totals range from 0 to 125, and many hospitals treat scores around 45 or higher as high risk, though thresholds vary. Other tools include the Hendrich II Fall Risk Model and the Johns Hopkins Fall Risk Assessment Tool. These scales are quick, but nurses usually score them only once a shift, they miss changes between assessments, and they label so many inpatients as at risk that the label loses meaning. Predictive models recalculate risk from EHR data as it changes. Inputs can include sedatives, opioids, diuretics and blood pressure medications, sodium levels, orthostatic vital signs, delirium screens, toileting needs, recent procedures and time of day. EHR vendors, including Epic, offer fall risk models, and some hospitals build their own. Video is a separate layer. Continuous virtual observation, offered by companies such as AvaSure, lets trained staff watch many rooms at once and speak to patients through a speaker. Newer systems add computer vision that spots posture changes such as sitting up or moving toward the bed edge. That gives earlier warning than pressure-pad bed alarms, which trigger only when weight comes off the mattress. A key misconception is that more alerts mean fewer falls. A large randomized trial of increased bed alarm use did not find a reduction in falls. A risk score says who might fall, not what to do. Falls drop when an alert leads to action: scheduled toileting, low beds, non-slip footwear, gait belts, physical therapy, medication review and staying with patients in the bathroom. Since 2008, CMS has not paid hospitals extra for falls with injury that happen during a stay, which gives hospitals a financial reason to prevent them.
A predictive model flags an older patient after a new sedative is started on top of a diuretic. The nurse starts scheduled toileting rounds and asks pharmacy to review the combination.
A computer vision system in a monitored room sees a patient sit up and swing their legs over the bed edge. It alerts a virtual observer, who talks to the patient through the speaker while a nurse walks to the room.
A unit reviews its model alerts and finds most flagged patients never fall. It raises the threshold for night-shift notifications to reduce alarm fatigue.
A nurse sees a high Morse score but a low model score on a patient who is steady but uses a walker. She relies on her own assessment and documents why.
Hospitals are likely to combine EHR risk scores with video monitoring and nurse call data, so that alerts reflect both who is at risk and what is happening in the room. Whether this reduces injurious falls, and not just falls recorded, needs better studies than most vendors have published so far. Privacy expectations, patient consent for cameras, and alarm fatigue will limit how widely continuous monitoring spreads. The approach that holds up is using predictions to target known prevention steps, with nurses keeping the authority to override scores.
Bản tin miễn phí
Ba câu chuyện AI đã được xác minh vào mỗi buổi sáng các ngày trong tuần, được viết bằng tiếng Anh đơn giản. Miễn phí mãi mãi, không có quảng cáo.
Một email mỗi ngày trong tuần. Hủy đăng ký trong một cú nhấp chuột. Chúng tôi không bao giờ bán hoặc chia sẻ địa chỉ của bạn.
Tự kiểm tra
Phản hồi tức thì về mọi câu trả lời và chứng chỉ có thể chia sẻ với ID có thể xác minh sau khi bạn vượt qua khóa học.
Hỗ trợ giáo dục AI miễn phí. AI Understanding là tổ chức phi lợi nhuận 501(c)(3) — không bao giờ có quảng cáo, không có tường phí. Hãy quyên góp
AI fall risk prediction uses electronic health record data, and sometimes in-room video, to estimate which hospital patients are likely to fall and alert staff early. It aims to improve on periodic bedside scores like the Morse Fall Scale. Falls cause injuries, longer stays and costs hospitals cannot recover, but an alert only helps if nurses can act on it without drowning in alarms.
The Morse Fall Scale scores six items: history of falling, secondary diagnosis, ambulatory aid, IV or saline lock, gait, and mental status.
When the outcome is rare, most flagged patients will not fall even if the model ranks them well. That is why the guide recommends reporting precision and alerts per true fall.
Pressure pads trigger when weight comes off the mattress. Vision systems can spot sitting up or moving toward the bed edge earlier, giving staff more time.
The trial did not show fewer falls with more bed alarms. This supports the guide's point that alerts must lead to prevention actions.
Falls with injury are among hospital-acquired conditions for which CMS does not pay extra. That gives hospitals a financial reason to prevent them.
Tiếp tục học hỏi
Đã chọn thêm hướng dẫn cho chủ đề này
Tiếp theoHướng dẫn tiếp theo
Dự đoán tái nhập viện AI
ngành công nghiệp