This dataset contains information on 1,071 in-hopsital falls that occurred between 2012 and 2017 at Hospital Moinhos de Vento, a 497-bed institution located in the city of Porto Alegre, Brazil.The reporting of falls in hospital settings is recognized as a prevention strategy for informing corrective actions with the aim of preventing future such events. To this end, this dataset contains a broad array of variables relating to each fall incident (note that not all years include each variable): * Date of incident* Birth decade of patient* Age range of patient* Sex of patient* Weekday of incident* Shift during which the incident ocurred* Hospital department or location of incident * Location or environment in which the incident ocurred* Severity of incident* Presence of companion at time of incident* Fall risk level as measured by the Johns Hopkins Fall Risk Assessment Tool* Involvement of medication associated with fall risk* Whether a fall prevention protocol was implemented* Type of injury incurred, if any* Reason for incident* Whether a restraint prescription was given * Whether a physical therapy prescription was givenThe data are presented as a single Excel XLSX file: hospital-fall-data-2012-2017.xlsx, separated into sheets according to year of data capture for the years 2012 - 2017.Learning about the characteristics of these events and establishing a profile may contribute to the design of adequate prevention and improvement strategies that effectively reduce the risk of falls.The project from which these data were extracted was approved by the institution’s research ethics committee (CAAE: 57679316.9.0000.5330 - approval 1.833.572).

National Audit of Inpatient Falls Data from clinical audit data from 1 January to 31 December 2024, published October 2025. Falls are the most frequently reported incident affecting hospital inpatients. The data collected by NAIF and presented below provide opportunity to identify areas in which to enhance the quality of care for people who sustain an inpatient hip fracture. This is the final NAIF report from the continuous audit of only those inpatients who had a fall resulting in a femoral fracture. In January 2025, NAIF expanded to collect data on all fractures, head injuries and spinal injuries that occurred as a result of an inpatient fall. The next report will therefore present national data on patients with these fall-related injuries.

ABSTRACT Objective To investigate the use of fall-risk-increasing drugs among patients with falls reported to the Patient Safety Office of a hospital, and to identify the factors associated with high risk for fall. Methods A cross-sectional study, carried out in a teaching hospital. The study population was the universe of fall reports received by the Patient Safety Office. The dependent variable was a high risk for falls. The Medication Fall Risk Score was used to measure fall risk. Descriptive, univariate and multivariate analyses were performed. Results Of the 125 fall reports in the study, 38 (30.4%) were in 2014, 26 (20.8%) in 2015, and 61 (48.8%) in 2016. Half of the patients (63; 50.4%) were classified as high fall risk and 74 (59.2%) had two or more risk factors for the event. The most frequently used drug classes were opioids (25%), anxiolytics (19.7%), beta-blockers (9.9%), angiotensin II antagonists (7%) and vascular-selective calcium channel blockers (7%). After the adjusted analysis, the factors associated with falls were amputation (odds ratio: 14.17), female sex (odds ratio: 2.98) and severe pain (odds ratio: 5.47). Conclusion Medications are an important contributor to in-hospital falls, and the Medication Fall Risk Score can help identify patients at a high risk for falls.

Falls are a major cause of Emergency Hospital Admissions for Older People, and lead to many moving from home into residential care. The highest risk of falls is in people aged 65 and over. Falls injuries can be particularly serious for older people, resulting in fractures and hospitalisation. Inpatient hospital admissions are a proportion of falls incidents, but more may present to Accident and Emergency and GPs, not all of which will lead to hospital admission. This indicator helps to measure falls prevention and joint working between the NHS, public health and social care. Directly Age-Standardised Rates (DASR) are shown in the data (where numbers are sufficient) so that rates can be directly compared between areas. The DASR calculation applies Age-specific rates to a Standard European population to cancel out possible effects on crude rates due to different age structures among populations, thus enabling direct comparisons of rates. This data uses primary diagnosis of injuries only. This may result in lower values in comparison to using all diagnoses. Data source: Office for Health Improvement and Disparities (OHID), Public Health Outcomes Framework (PHOF) indicator 2.24i (22401-C29). This data is updated annually.

Inpatient falls are common and remain a great challenge for the NHS. Falls in hospital are the most commonly reported patient safety incidents, with more than 240,000 reported in acute hospitals and mental health trusts in England and Wales every year (that is over 600 a day). All falls, even those that do not result in injury, can cause older patients and their family to feel anxious and distressed. For those who are frail, minor injuries from a fall can affect their physical function, resulting in reduced mobility, and undermining their confidence and independence. Some falls in hospital result in serious injuries, such as hip fracture (more than 3,000 per year) and serious head injuries, and these injuries can result in death. Falls in hospitals are financially expensive, as they increase the length of stay and may require increased care costs upon discharge. In 2007, inpatient falls were thought to cost trusts alone £15 million, and will be more expensive now. Tackling the problem of inpatient falls is challenging. There are no single or easily defined interventions which, when done on their own, are shown to reduce falls. However, research has shown that multiple interventions performed by the multidisciplinary team and tailored to the individual patient can reduce falls by 20–30%. These interventions are particularly important for patients with dementia or delirium, who are at high risk of falls in hospitals.

This dataset contains the statewide composite patient safety and Adverse Events indicator (PSI) rate used to determine the “Incidence of measurable hospital-acquired conditions” rate for the Let’s Get Healthy California Initiative. PSI rates may not be comparable across years as significant changes were made to composition, definition, and calculation of PSI over time. The current composite PSI includes the following component indicators: pressure ulcer, iatrogenic pneumothorax, in-hospital fall-associated fracture, postoperative hemorrhage or hematoma, postoperative acute kidney injury requiring dialysis, postoperative respiratory failure, perioperative pulmonary embolism or deep vein thrombosis, postoperative sepsis, postoperative wound dehiscence, abdominopelvic accidental puncture or laceration.

ABSTRACT Background: Falls are a major problem in public health since they are an important cause of morbidity and mortality. To evaluate the risk of fall and prescribe preventive interventions may be a challenging task. Objectives: The objectives of this study are to summarize the most relevant information on the topic “falls in the elderly” and to give a critical view and practical clinical approach on this topic. Methods: In March 2022, a search of Pubmed database was performed, using the terms “fall elderly”, fall prevention”, “fall risk”, with the following parameters: five years, review, systematic review, meta-analysis, practice guidelines. Results: There are several risk factors for falls that can be grouped in different areas (psychosocial, demographic, medical, medication, behavioral, environmental). The clinical evaluation of an older adult prone to falls must include identification of risk factors through history and examination and identification of risk of falls through an assessment tool such as gait velocity, functional reach test, timed up and go, Berg balance test, and miniBEST test. Fall prevention strategies can be single or multiple, and physical activity is the most cited. Technology can be used to detect and prevent falls. Conclusion: A systematic approach to the older patient in risk of falls is feasible and may impact fall prevention.

The National Audit of Inpatient Falls (NAIF) is designed to capture data from acute, community and mental health hospitals relating to falls, and is based on NICE guidance and advice from NHS Improvement (NHSI). Hospital inpatients in England experienced a quarter of a million falls during the year 2015/16.1 These were spread across acute, community and mental health hospitals. Falls are commonly reported patient safety incidents and result in:  over 2,500 hip fractures2  loss of confidence and slower recovery, even when physical harm is minimal  distress to families and staff  litigation against hospital trusts  overall costs to hospitals of £630 million per year. Acute illness, particularly in frail older people or those recovering from serious injury or surgery, increases the risk of a fall in hospital. Patients are vulnerable to delirium, dehydration and deconditioning, all of which affect balance and mobility, especially in unfamiliar surroundings. The majority of falls occur among medical inpatients during the first few days after admission. These circumstances mean that not all falls are preventable. However, successful implementation of guidance from NICE may prevent 20–30% of falls.4 Prevention depends upon prompt assessment to identify potential risk factors, followed by clinical responses to ameliorate their effects. This is a complex task requiring a multidisciplinary team approach. One patient may require several individually tailored interventions. It also requires a patient safety approach throughout the organisation, with practical support such as walking aids being always available, a culture of reliable incident reporting, and clear accountability and commitment from senior leaders. The National Audit of Inpatient Falls (NAIF) was designed to capture all these elements. It is based on NICE guidance and advice from NHS Improvement (NHSI).

In the period 2022/23, there were around 12.6 thousand admittance among females aged 75 years and over in Scotland as the result of a fall. This statistic shows the number of emergency hospital admissions as the result of a fall in Scotland in 2022/23, by age and gender.

Objectives: To clarify the risk factors for falls in hospital settings and to propose the use of such factors to identify high-risk persons at admission. Design: Prospective cohort study. Setting: Fukushima Medical University Hospital, Japan, from August 2008 and September 2009. Participants: 9957 adult consecutive inpatients admitted to our hospital. Methods: Information was collected at admission from clinical records obtained from a structured questionnaire conducted in face-to-face interviews with subjects by nurses and doctors and fall events were collected from clinical records.Results: The proportion of patients who fell during follow-up was 2.5% and the incidence of falls was 3.28 per 100 person-days. There were significant differences in age, history of falling, cognitive dysfunction, planned surgery, wheelchair use, need for help to move, use of a remote caring system, rehabilitation, use of laxative, hypnotic or psychotropic medications and need for help with activities of daily living (ADL) between patients who did and did not fall. Multivariable adjusted ORs for falls showed that age, history of falls and need for help with ADL were common risk factors in both men and women. Using psychotropic medication also increased the risk of falling in men while cognitive dysfunction and use of hypnotic medication increased the risk of falling in women. Planned surgery was associated with a low risk of falls in women. Conclusions: To prevent falls in inpatients it is important to identify high-risk persons. Age, history of falling and the need for help with ADL are the most important pieces of information to be obtained at admission. Care plans for patients including fall prevention should be clear and considered.

Abstract Falls are the second leading cause of accidental and unintentional injury deaths worldwide. Inpatient falls in hospital settings are likely to prolong the length of stay of patients in nearly 6.3 days, leading to increased hospitalization costs. The causes of fall incidents in healthcare facilities are multifactorial in nature and certain medications use could be associated with these incidents. This review seeks to critically evaluate the available literature regarding the relationship between inpatient falls and medication use. A comprehensive search was performed on MEDLINE, EMBASE and Lilacs with no time restriction. The search was filtered using English, Spanish or Portuguese languages. Our study evaluated medication use and inpatients falls that effectively happen, considering all ages and populations. An assessment of bias and quality of the studies was carried out using an adapted tool from the literature. The drugs were classified according to the Anatomic Therapeutics Chemical Code. The search strategy retrieved 563 records, among which 23 met the eligibility criteria; ninety three different pharmacological subgroups were associated with fall incidents. Our critical review suggests that the use of central nervous system drugs (including anxiolytics; hypnotics and sedatives; antipsychotics; opioids; antiepileptics and antidepressants) has a greater likelihood of causing inpatient falls. A weak relationship was found between other pharmacological subgroups, such as diuretics, cardiovascular system-related medications, and inpatient fall. Remarkably, several problems of quality were encountered with regard to the eligible studies. Among such quality problems included retrospective design, the grouping of more than one medication in the same statistical analysis, limited external validity, problems related to medication classifications and description of potential confounders.

In 2022/23, over eight thousand emergency admittance due to falls among adults were diagnosed with a fractured femur. This statistic shows the number of emergency hospital admissions among adults due to a fall in Scotland in 2022/23, by main diagnosis.

This dataset presents the age-standardised rate of emergency hospital admissions due to falls in individuals aged 65 and over. It serves as a key indicator of frailty, injury risk, and the effectiveness of fall prevention strategies in older populations.

Rationale Reducing emergency admissions due to falls in older adults is a major public health priority. Falls are a leading cause of injury, loss of independence, and mortality in this age group. Monitoring this indicator supports the development of targeted interventions, community support services, and healthcare planning to reduce fall-related harm.

Numerator The numerator is the number of emergency hospital admissions for individuals aged 65 and over with a primary diagnosis of injury (ICD-10 codes S00 to T98) and an external cause of a fall (ICD-10 codes W00 to W19). Admissions are included if they are emergency admissions (episode order = 1, admission method starts with '2'). Data are sourced from the Secondary Uses Service (SUS).

Denominator The denominator is the resident population aged 65 and over, based on the 2021 Census.

Caveats In 2023, NHS England introduced a methodological change requiring Trusts to report Same Day Emergency Care (SDEC) to the Emergency Care Data Set (ECDS) by July 2024. Early adopter sites began reporting from 2021/22, with others following in 2022/23 and 2023/24. Some Trusts previously reported this activity under Admitted Patient Care, and the shift to ECDS may reduce the number of admissions captured by this indicator. NHSE has advised that SDEC activity cannot currently be accurately identified in existing data flows, and the impact of this change is expected to vary by diagnosis, particularly for injuries and external causes.

External References Fingertips Public Health Profiles – Emergency Admissions for Falls (65+)

Localities ExplainedThis dataset contains data based on either the resident locality or registered locality of the patient, a distinction is made between resident locality and registered locality populations:Resident Locality refers to individuals who live within the defined geographic boundaries of the locality. These boundaries are aligned with official administrative areas such as wards and Lower Layer Super Output Areas (LSOAs).Registered Locality refers to individuals who are registered with GP practices that are assigned to a locality based on the Primary Care Network (PCN) they belong to. These assignments are approximate—PCNs are mapped to a locality based on the location of most of their GP surgeries. As a result, locality-registered patients may live outside the locality, sometimes even in different towns or cities.This distinction is important because some health indicators are only available at GP practice level, without information on where patients actually reside. In such cases, data is attributed to the locality based on GP registration, not residential address.

Click here to explore more from the Birmingham and Solihull Integrated Care Partnerships Outcome Framework.

AI Fall Risk Prediction in Hospitals Market Outlook

According to the latest research, the AI Fall Risk Prediction in Hospitals market size reached USD 1.23 billion globally in 2024, with a robust compound annual growth rate (CAGR) of 22.7% expected through the forecast period. By 2033, the market is projected to achieve a value of USD 9.61 billion, reflecting the increasing adoption of artificial intelligence in healthcare environments to enhance patient safety and operational efficiency. The primary growth factor fueling this expansion is the rising need for proactive fall prevention strategies in hospitals, driven by the aging global population and the high costs associated with fall-related injuries.

The growth of the AI Fall Risk Prediction in Hospitals market is largely attributed to the escalating demand for advanced patient safety solutions. Hospitals worldwide are under immense pressure to minimize adverse events, particularly falls, which remain a leading cause of injury and prolonged hospital stays. AI-driven fall risk prediction systems leverage machine learning algorithms and real-time patient data to identify individuals at high risk of falling, enabling timely interventions. This proactive approach not only enhances patient outcomes but also reduces the financial burden on healthcare systems by preventing costly complications. The growing awareness among healthcare providers about the benefits of AI-powered risk prediction tools is further accelerating market growth, as institutions seek to improve care quality while adhering to stringent regulatory standards.

Another significant driver is the integration of AI technologies with existing hospital information systems and medical devices. As electronic health records (EHRs), wearable sensors, and remote monitoring tools become more prevalent, the volume of patient data available for analysis has surged. AI-based fall risk prediction platforms can synthesize this data to deliver actionable insights, supporting clinical decision-making and workflow optimization. The seamless interoperability offered by modern AI solutions encourages hospitals to invest in these technologies, knowing they can be efficiently integrated into current infrastructures. Additionally, the shift towards value-based healthcare models incentivizes providers to adopt predictive analytics, as preventing falls directly correlates with improved patient satisfaction scores and reduced readmission rates.

The market is also benefiting from increased investments in healthcare IT and ongoing advancements in machine learning algorithms. Governments and private entities are allocating substantial resources to digital health initiatives, recognizing the potential of AI to transform patient care delivery. These investments are fostering innovation, resulting in more accurate, scalable, and user-friendly fall risk prediction solutions. Furthermore, the COVID-19 pandemic has underscored the importance of remote patient monitoring and early risk detection, prompting hospitals to accelerate their digital transformation efforts. As a result, the adoption of AI fall risk prediction systems is expected to remain on an upward trajectory, supported by favorable regulatory frameworks and growing acceptance among clinicians.

From a regional perspective, North America currently dominates the AI Fall Risk Prediction in Hospitals market, accounting for the largest share due to its advanced healthcare infrastructure, high adoption of digital health technologies, and supportive policy environment. However, the Asia Pacific region is anticipated to witness the fastest growth during the forecast period, driven by increasing healthcare investments, rising geriatric population, and expanding hospital networks. Europe also holds a significant market share, supported by robust government initiatives aimed at improving patient safety and promoting technological innovation in healthcare. Latin America and the Middle East & Africa are gradually emerging as promising markets, as healthcare providers in these regions recognize the value of AI-driven fall prevention solutions in addressing local healthcare challenges.

Component Analysis

The AI Fall Risk Prediction in Hospitals market is segmented by component into software, hardware, and services, each playing a critical role in the deployment and effectiveness

IntroductionFalls are the leading cause of injury in older people. Reducing falls could reduce financial pressures on health services. We carried out this research to develop a falls risk model, using routine primary care and hospital data to identify those at risk of falls, and apply a cost analysis to enable commissioners of health services to identify those in whom savings can be made through referral to a falls prevention service.MethodsMultilevel logistical regression was performed on routinely collected general practice and hospital data from 74751 over 65’s, to produce a risk model for falls. Validation measures were carried out. A cost-analysis was performed to identify at which level of risk it would be cost-effective to refer patients to a falls prevention service. 95% confidence intervals were calculated using a Monte Carlo Model (MCM), allowing us to adjust for uncertainty in the estimates of these variables.ResultsA risk model for falls was produced with an area under the curve of the receiver operating characteristics curve of 0.87. The risk cut-off with the highest combination of sensitivity and specificity was at p = 0.07 (sensitivity of 81% and specificity of 78%). The risk cut-off at which savings outweigh costs was p = 0.27 and the risk cut-off with the maximum savings was p = 0.53, which would result in referral of 1.8% and 0.45% of the over 65’s population respectively. Above a risk cut-off of p = 0.27, costs do not exceed savings.ConclusionsThis model is the best performing falls predictive tool developed to date; it has been developed on a large UK city population; can be readily run from routine data; and can be implemented in a way that optimises the use of health service resources. Commissioners of health services should use this model to flag and refer patients at risk to their falls service and save resources.

The FFFAP NAIF is a continuously ascertained, record-level audit which evaluates both falls prevention activity prior to the hip fracture and post-falls care, when inpatients have fallen within acute, community and mental health hospital care in England and Wales. Data collection started in January 2019.

ABSTRACT OBJECTIVE To estimate the trends of fall-related hospitalization, mortality, and lethality among older adults in Brazil and regions. METHODS This is a descriptive study based on data from the Hospital Information System of the Brazilian Unified Health System. We included records of every older adult, aged 60 years or older, hospitalized for accidental fall from January, 1998 to November, 2015 in all Brazilian regions. We selected the codes E885, E886, E880, E884, E884 from the International Classification of Diseases, 9th revision, and W01, W03, W10, W17, W18 from the 10th revision, and calculated fall-related hospitalization and mortality rates per 100,000 inhabitants, as well as lethality. To estimate trends, we applied the Prais-Winsten regression for time series analysis. RESULTS During the period, 1,192,829 fall-related hospitalizations occurred, among which 54,673 had a fatal outcome; lethality was 4.5%. Hospitalization rates showed upward trends, with seasonality, in Brazil (11%), and in the Northeast (44%), Midwest (13%), and South regions (14%). The North showed a decreasing hospitalization rate (48%), and the Southeast a stationary one (3%). CONCLUSIONS In Brazil, fall-related hospitalizations, mortality, and lethality among older adults showed an upward trend from 1998 to 2015, with seasonal peaks in the second and third quarters. Considering we are in plain demographic transition, to improve hospital healthcare and encourage falls prevention programs among older adults is essential.

Suggested fall prevention strategies in the SCI unit.

This dataset contains multi-sensor recordings from wearable and environmental devices, capturing motion, heart rate, posture, and room conditions. It includes fall events labeled by severity and risk level, supporting real-time patient monitoring and alert generation. Key Features:

Multi-sensor data from wearable devices (accelerometer, gyroscope, heart rate)

Environmental context: room temperature, room type, and other conditions

Posture information: patient posture and transitions

Fall events: labeled with severity and risk level

Supports time-series analysis of patient motion and vitals

Enables real-time monitoring and context-aware alert generation

Suitable for pattern recognition, anomaly detection, and predictive modeling

National Audit of Inpatient Falls Data from March 2020 facilities audit, reported on in Interim Annual Report, published May 2021. Falls are the most frequently reported incident affecting hospital inpatients, with 247,000 falls occurring in inpatient settings each year in England alone (NHS Improvement). The data collected by NAIF and presented below provide opportunity to identify areas in which to enhance the quality of care for people who sustain an inpatient hip fracture. In April 2020, due to the COVID-19 pandemic, submission of audit data was made non-mandatory. To help organisations catch up with data inputting, NAIF extended the clinical audit deadline to the end of 2020. This means that instead of publishing a single report combining clinical and facilities data, this interim report describes facilities data (facilities audit open March to August 2020) and further analysis of inpatient hip fractures from the National Hip Fracture Database. Clinical data will be published in a separate report in Autumn 2021.