1
|
Braun BJ, Histing T, Menger MM, Herath SC, Mueller-Franzes GA, Grimm B, Marmor MT, Truhn D. Wearable activity data can predict functional recovery after musculoskeletal injury: Feasibility of a machine learning approach. Injury 2024; 55:111254. [PMID: 38070329 DOI: 10.1016/j.injury.2023.111254] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Revised: 10/23/2023] [Accepted: 11/26/2023] [Indexed: 01/29/2024]
Abstract
Delayed functional recovery after injury is associated with significant personal and socioeconomic burden. Identification of patients at risk for a prolonged recovery after a musculoskeletal injury is thus of high relevance. The aim of the current study was to show the feasibility of using a machine learning assisted model to predict functional recovery based on the pre- and immediate post injury patient activity as measured with wearable systems in trauma patients. Patients with a pre-existing wearable (smartphone and/or body-worn sensor), data availability of at least 7 days prior to their injury, and any musculoskeletal injury of the upper or lower extremity were included in this study. Patient age, sex, injured extremity, time off work and step count as activity data were recorded continuously both pre- and post-injury. Descriptive statistics were performed and a logistic regression machine learning model was used to predict the patient's functional recovery status after 6 weeks based on their pre- and post-injury activity characteristics. Overall 38 patients (7 upper extremity, 24 lower extremity, 5 pelvis, 2 combined) were included in this proof-of-concept study. The average follow-up with available wearable data was 85.4 days. Based on the activity data, a predictive model was constructed to determine the likelihood of having a recovery of at least 50 % of the pre-injury activity state by post injury week 6. Based on the individual activity by week 3 a predictive accuracy of over 80 % was achieved on an independent test set (F1=0,82; AUC=0,86; ACC=8,83). The employed model is feasible to assess the principal risk for a slower recovery based on readily available personal wearable activity data. The model has the potential to identify patients requiring additional aftercare attention early during the treatment course, thus optimizing return to the pre-injury status through focused interventions. Additional patient data is needed to adapt the model to more specifically focus on different fracture entities and patient groups.
Collapse
Affiliation(s)
- Benedikt J Braun
- University Hospital Tuebingen, Eberhard-Karls-University Tuebingen, BG Unfallklinik, Schnarrenbergstr. 95, Tuebingen 72076, Federal Republic of Germany.
| | - Tina Histing
- University Hospital Tuebingen, Eberhard-Karls-University Tuebingen, BG Unfallklinik, Schnarrenbergstr. 95, Tuebingen 72076, Federal Republic of Germany
| | - Maximilian M Menger
- University Hospital Tuebingen, Eberhard-Karls-University Tuebingen, BG Unfallklinik, Schnarrenbergstr. 95, Tuebingen 72076, Federal Republic of Germany
| | - Steven C Herath
- University Hospital Tuebingen, Eberhard-Karls-University Tuebingen, BG Unfallklinik, Schnarrenbergstr. 95, Tuebingen 72076, Federal Republic of Germany
| | - Gustav A Mueller-Franzes
- Departments of Diagnostic and Interventional Radiology, RWTH Aachen University Aachen, Aachen, Federal Republic of Germany
| | - Bernd Grimm
- Orthopaedic Trauma Institute (OTI), University of California, San Francisco General Hospital, San Franci-sco, CA, USA
| | - Meir T Marmor
- Department of Precision Health, Human Motion, Orthopaedics, Sports Medicine and Digital Methods Group, Lux-embourg Institute of Health, Strassen 1445, Luxembourg
| | - Daniel Truhn
- Departments of Diagnostic and Interventional Radiology, RWTH Aachen University Aachen, Aachen, Federal Republic of Germany
| |
Collapse
|
2
|
Bartram MC, Kanngießer J, Hufendiek K, Schalhorn C, Framme C. [Testing for visual deficits by the police among road users in Germany]. DIE OPHTHALMOLOGIE 2024; 121:18-26. [PMID: 37783760 DOI: 10.1007/s00347-023-01928-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Revised: 08/08/2023] [Accepted: 08/31/2023] [Indexed: 10/04/2023]
Abstract
BACKGROUND The Professional Association of Ophthalmologists (BVA) estimates that at least 100,000s of traffic accidents with 10,000s of injuries and fatalities are caused by known and unknown visual disorders on German roads every year. Until now, however, the police have not had the opportunity to check for potential visual disorders on the spot in cases of conspicuous driving. In a pilot project of the police with the Eye Hospital of the Hannover Medical School (MHH), the aim was for the first time to extend the existing tests of the police by adapted "car-side" vision tests. MATERIAL AND METHOD On-site evaluation of eye motility, pupil size and light reaction of car drivers as well as an orienting visual acuity test and an orienting confrontation visual field was performed. The practical performance of all examination modalities was previously coordinated and trained. RESULTS The scope and type of individual examinations for estimating visual ability of car drivers were described and standardized. In addition to the visual characteristics, more familiar neurological tests, such as walking along a straight line were also recorded. The combined test evaluation results in an objective basis for the official decision of an immediate temporary withdrawal of the driving license, if necessary, and the initiation of further measures, such as an ophthalmological examination. With these innovations, the Lower Saxony police have revised their training concept for checking driving ability and issued it for implementation at the beginning of 2022, including the vision tests recommended by ophthalmologists. In the meantime, around 150 officers have been trained in Lower Saxony and are now authorized to carry out qualified driving ability tests. In this respect, a large number of corresponding traffic examinations have already been carried out and the continued driving of road users with significant visual deficits has been prevented. CONCLUSION In this pilot project, the aim was for the first time to expand the common testing procedures of the traffic police for the detection of drivers who are dangerous to traffic, in addition to screening for alcohol, drugs and neurological deficits, to include specific tests for the detection of visual deficits. The corresponding training of police officers has been carried out across the board in Lower Saxony and Hamburg, and the measures are currently being applied as needed during traffic controls. In the future, the tested characteristics will be evaluated in a weighted score and will provide an objective basis for the police to decide whether to stop the driver in cases of deficits.
Collapse
Affiliation(s)
- M C Bartram
- Universitätsklinik für Augenheilkunde, Medizinische Hochschule Hannover, Hannvover, Deutschland
| | - J Kanngießer
- Autobahnpolizei Niedersachsen, Hildesheim, Deutschland
| | - K Hufendiek
- Universitätsklinik für Augenheilkunde, Medizinische Hochschule Hannover, Hannvover, Deutschland
| | - C Schalhorn
- Polizeiakademie Hamburg, Hamburg, Deutschland
| | - C Framme
- Universitätsklinik für Augenheilkunde, Medizinische Hochschule Hannover, Hannvover, Deutschland.
| |
Collapse
|
3
|
Michael M, Al Agha S, Böhm L, Bosse HM, Pohle AN, Schürmann J, Hannappel O, Tengg E, Weiß C, Bernhard M. Alters- und geschlechtsbezogene Verteilung von Zuführung, Ersteinschätzung, Entlassart und Verweildauer in der zentralen Notaufnahme. Notf Rett Med 2021. [DOI: 10.1007/s10049-021-00895-9] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023]
Abstract
Zusammenfassung
Einleitung
Jährlich stellen sich bundesweit zahlreiche Patienten in zentralen Notaufnahmen vor. Ziel der vorliegenden Untersuchung war es, alters- und geschlechtsabhängig Zuführung, Ersteinschätzung, Entlassart und Verweildauer an einem universitären Standort zu analysieren.
Material und Methodik
In dieser retrospektiven Studie wurden alle Patientenkontakte der zentralen Notaufnahme des Universitätsklinikums Düsseldorf des Jahres 2019 erfasst und anhand der Prozesskriterien Zuführung, Ersteinschätzung, Entlassart und Verweildauer kategorisiert und deren Verteilung untersucht.
Ergebnisse
Vom 01.01. bis 31.12.2019 wurden insgesamt 43.821 Patientenkontakte erfasst. Das durchschnittliche Alter der Patienten betrug 47 ± 24 Jahre (Median: 47, Min.–Max.: 0–106). Der Anteil weiblicher Patienten betrug 48 %. Ein Alter ≤ 17 Jahren wiesen 10 % der Patienten (♀ vs. ♂: 4 vs. 6 %, p < 0,0001) und ein Alter ≥ 70 Jahre 24 % auf (♀ vs. ♂: 13 vs. 11 %, p < 0,0001). Für beide Geschlechter nahm der Anteil der Triagekategorien „blau“ und „grün“ über die aufsteigenden Altersgruppen stetig ab. Ab der Altersgruppe der 50- bis 59-Jährigen lag für beide Geschlechter führend eine höhere Dringlichkeit („gelb“ bis „rot“) vor. Während im Alter ≤ 17 Jahren mit 84–90 % vorwiegend eine ambulante Behandlung erfolgte, reduzierte sich dieser Anteil über die weiteren Altersgruppen bis auf 22 % bei Männern und 28 % bei Frauen in der Altersgruppe der ≥ 90-Jährigen. Für die drei Entlassarten „ambulant“, „prästationär“ und „stationär“ stieg die Verweildauer bei beiden Geschlechtern mit dem Alter kontinuierlich an.
Schlussfolgerung
Es finden sich deutliche und vor allem altersabhängige Unterschiede in den Prozesskriterien Zuführung, Ersteinschätzung, Entlassart und Verweildauer. Rund 15 % der Patienten sind kritisch krank oder verletzt („orange“ und „rot“). Mit steigendem Alter nimmt der Anteil dieser Triagekategorien zu. Bei rund 30 % der Patienten besteht eine stationäre Aufnahmeindikation, entsprechende Bettenkapazitäten müssen täglich eingeplant werden.
Collapse
|
4
|
Pu H, Li B, Luo D, Wang S, Wang Z, Zhao W, Zheng L, Duan P. Impact of urbanization factors on mortality due to unintentional injuries using panel data regression model and spatial-temporal analysis. ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH INTERNATIONAL 2020; 27:2945-2954. [PMID: 31838677 DOI: 10.1007/s11356-019-07128-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/28/2019] [Accepted: 11/19/2019] [Indexed: 06/10/2023]
Abstract
Unintentional injuries pose a great risk for human health in China. Few studies have focused on unintentional injuries at national level from urbanization perspective. The panel data of mortality rate of transportation accidents (TA), fall and drowning and sinking (DS) is investigated, and urbanization development index is collected. Global Moran's I and linear regression of panel data are applied to determine the spatial distribution and spatial influencing factors of unintentional injuries. The results are the following: (1) The unintentional injury such as TA, fall, and DS shows clear non-uniformity of spatial distribution and relative immobility through time. (2) A 10,000 tons increase in SO2 emission amount (SO2 EA) and emission of smoke and dust (ESD) can result in 15.7 and 12.5 increases in TA death in eastern region, respectively. Meanwhile, A 10,000 tons increase in NOx emission amount can cause 15.1 increase in TA death in western region. For every 100 billion yuan increase in GDP, the fall death can reduce by 8.4 in central region. One bed increase in number of hospital beds per 10,000 population (NHBP) is favorable for decreasing in fall death by 16.7 in eastern region. However, increase in number of workers enjoying industrial injury (NEWII) does not reduce the fall death in eastern region. (3) For every 1 ten thousand people increase in number of students in ordinary high schools (NSOHS) is conductive to reducing DS death by 7.8 in the western region. Our findings show that there exist spatial differences for urbanization influencing TA, fall, and DS death in eastern, western, and central regions. This study is expected to provide a reference for unintentional injuries control in those three regions.
Collapse
Affiliation(s)
- Haixia Pu
- Research Center of the Economy of the Upper Reaches of the Yangtze River and the Key Research Base of Humanities, Ministry Of Education, Chongqing Technology and Business University, Chongqing, 400067, China
- College of Tourism and Land Resources, Chongqing Technology and Business University, Chongqing, 400067, China
- Chongqing Key Laboratory of Spatial Data Mining and Big Data Integration for Ecology and Environment, Chongqing, China
| | - Bin Li
- Research Center of the Economy of the Upper Reaches of the Yangtze River and the Key Research Base of Humanities, Ministry Of Education, Chongqing Technology and Business University, Chongqing, 400067, China
| | - Dongqi Luo
- Research Center of the Economy of the Upper Reaches of the Yangtze River and the Key Research Base of Humanities, Ministry Of Education, Chongqing Technology and Business University, Chongqing, 400067, China.
| | - Shaobin Wang
- Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, 100101, China
| | - Zhaolin Wang
- Research Center of the Economy of the Upper Reaches of the Yangtze River and the Key Research Base of Humanities, Ministry Of Education, Chongqing Technology and Business University, Chongqing, 400067, China
| | - Wei Zhao
- Research Center of the Economy of the Upper Reaches of the Yangtze River and the Key Research Base of Humanities, Ministry Of Education, Chongqing Technology and Business University, Chongqing, 400067, China
| | - Lingyu Zheng
- Research Center of the Economy of the Upper Reaches of the Yangtze River and the Key Research Base of Humanities, Ministry Of Education, Chongqing Technology and Business University, Chongqing, 400067, China
| | - Ping Duan
- College of Tourism and Geographic Sciences, Yunnan Normal University, Kunming, 650500, Yunnan, China
| |
Collapse
|
5
|
Wengler A, Rommel A, Plaß D, Gruhl H, Leddin J, Porst M, Anton A, von der Lippe E. [ICD coding of causes of death: challenges for calculating the burden of disease in Germany]. Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz 2019; 62:1485-1492. [PMID: 31758220 DOI: 10.1007/s00103-019-03054-1] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
Abstract
In the project BURDEN 2020 - "The burden of disease in Germany and its regions" - the years of life lost (YLL) due to premature mortality are calculated on the basis of official cause-of-death statistics. This requires the identification and redistribution of the so-called ill-defined ICD codes. "Ill-defined" means that an ICD code does not sufficiently reflect the cause of death, such that it is not informative for the calculation of the burden of disease.The first steps on the way to calculating cause-specific YLL are presented. Different frameworks of ill-defined codes are compared. The number of deaths with ill-defined codes that can be found in the German cause-of-death statistics in absolute and relative terms are analyzed, including how they are distributed by age, sex, and region.According to the WHO framework, 15.6% of the 925,200 deaths in Germany in 2015 can be identified as ill-defined. According to the framework of the Institute for Health Metrics and Evaluation (IHME) in the Global Burden of Disease Study (GBD), the proportion of ill-defined codes is 26.6%. The ICD-related distribution patterns hardly differ between WHO and IHME classifications. Considerable differences exist between the federal states, with shares of ill-defined codes between 16 and 35% (IHME framework).The cause-of-death statistics in Germany contain a considerable proportion of ill-defined codes. The differences between the federal states can only partially be explained by different electronic data processing. Due to further dissemination and improvement of electronic data collection, higher quality of cause-of-death statistics can be expected in the future.
Collapse
Affiliation(s)
- Annelene Wengler
- Abteilung für Epidemiologie und Gesundheitsmonitoring, FG24 Gesundheitsberichterstattung, Robert Koch-Institut, Postfach 650261, 13302, Berlin, Deutschland.
| | - Alexander Rommel
- Abteilung für Epidemiologie und Gesundheitsmonitoring, FG24 Gesundheitsberichterstattung, Robert Koch-Institut, Postfach 650261, 13302, Berlin, Deutschland
| | - Dietrich Plaß
- Fachgebiet Expositionsschätzung, gesundheitsbezogene Indikatoren, Umweltbundesamt, Berlin, Deutschland
| | - Heike Gruhl
- Fachgebiet Expositionsschätzung, gesundheitsbezogene Indikatoren, Umweltbundesamt, Berlin, Deutschland
| | - Janko Leddin
- Abteilung für Epidemiologie und Gesundheitsmonitoring, FG24 Gesundheitsberichterstattung, Robert Koch-Institut, Postfach 650261, 13302, Berlin, Deutschland
| | - Michael Porst
- Abteilung für Epidemiologie und Gesundheitsmonitoring, FG24 Gesundheitsberichterstattung, Robert Koch-Institut, Postfach 650261, 13302, Berlin, Deutschland
| | - Aline Anton
- Abteilung für Epidemiologie und Gesundheitsmonitoring, FG24 Gesundheitsberichterstattung, Robert Koch-Institut, Postfach 650261, 13302, Berlin, Deutschland
| | - Elena von der Lippe
- Abteilung für Epidemiologie und Gesundheitsmonitoring, FG24 Gesundheitsberichterstattung, Robert Koch-Institut, Postfach 650261, 13302, Berlin, Deutschland
| |
Collapse
|
6
|
Fatal falls in the elderly and the presence of proximal femur fractures. Int J Legal Med 2018; 132:1699-1712. [PMID: 29882059 DOI: 10.1007/s00414-018-1876-7] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2017] [Accepted: 05/29/2018] [Indexed: 01/24/2023]
Abstract
Fatal falls are frequent and seem to be an increasing problem in the elderly. Especially ground level falls (GLFs) and falls on or from stairs and steps (stairs falls) are worth examining for forensic classification and in order to improve the development of preventive measures. We retrospectively analyzed 261 fatal falls of elderly age 65 + years, which were autopsied at the Institute of Legal Medicine in Munich between 2008 and 2014. After careful screening, the sub-set of all 77 GLFs and 39 stairs falls were analyzed towards socio-demographic characteristics, fall circumstances, injuries, and circumstances of death. A subsequent analysis of GLF cases regarding the presence of proximal femur fractures (PFF) was performed. The injury pattern of the GLFs and the stairs falls clearly differ with a higher share of injuries to the lower extremities in the GLFs. However, the most severely injured body region was the head in both groups (62% of the stairs cases, 49% of the GLF cases). Alcohol as contributing to the fall was seen more frequently in the stairs falls. PFF were not seen in the stairs falls, but then in 18 GLF cases. Yet, for 17 among them (22% of 77), their hip fracture was the only serious injury leading to hospitalization and death. Only one GLF case was already found dead. This finding indicates a potential of avoiding up to 22% of the GLF fatalities by preventing hip fractures by optimized hip protectors or other measures, especially for the elderly aged 75 + years.
Collapse
|
7
|
Risk factors for unintentional injuries among the rural elderly: a county-based cross-sectional survey. Sci Rep 2017; 7:12533. [PMID: 28970549 PMCID: PMC5624936 DOI: 10.1038/s41598-017-12991-3] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2017] [Accepted: 09/14/2017] [Indexed: 01/17/2023] Open
Abstract
This study aimed to provide evidence for the prevention and reduction of unintentional injuries in the rural elderly by analysing epidemiological data of injuries among rural older adults (65+) and identifying the involved risk and protective factors. This study analysed all information, including the social demographic characteristics, chronic disease condition, lifestyle, living environment, mental health, activities of daily living and detailed information about the nature of the injuries. Chi-square tests, rank tests and a multivariate logistic regression were performed. The prevalence of unintentional injuries was 44.4%; according to the multivariate regression analysis, ten variables, including gender, floor tiles, cane use, sleeping duration, roughage intake frequency, mental health status, diabetes, arthritis and cataracts, were involved in the injury patterns. Low roughage intake (OR = 2.34, 95% CI 1.64-3.35), the use of a cane (OR = 1.78, 95% CI 1.31-2.41), a sleeping duration of five hours (OR = 1.75, 95% CI 1.27-2.42) and severe mental disorders (OR = 1.61, 95% CI 1.01-2.57) were the top 4 risk factors. In conclusion, we found that unintentional injuries among the rural elderly were closely related to chronic disease, mental health and residence environment. These findings could be beneficial for the prevention of unintentional injuries and for policy makers and health service managers.
Collapse
|
8
|
Rommel A, Varnaccia G, Lahmann N, Kottner J, Kroll LE. Occupational Injuries in Germany: Population-Wide National Survey Data Emphasize the Importance of Work-Related Factors. PLoS One 2016; 11:e0148798. [PMID: 26859560 PMCID: PMC4747528 DOI: 10.1371/journal.pone.0148798] [Citation(s) in RCA: 28] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2015] [Accepted: 01/22/2016] [Indexed: 12/12/2022] Open
Abstract
Unintentional injuries cause much of the global mortality burden, with the workplace being a common accident setting. Even in high-income economies, occupational injury figures remain remarkably high. Because risk factors for occupational injuries are prone to confounding, the present research takes a comprehensive approach. To better understand the occurrence of occupational injuries, sociodemographic factors and work- and health-related factors are tested simultaneously. Thus, the present analysis aims to develop a comprehensive epidemiological model that facilitates the explanation of varying injury rates in the workplace. The representative phone survey German Health Update 2010 provides information on medically treated occupational injuries sustained in the year prior to the interview. Data were collected on sociodemographics, occupation, working conditions, health-related behaviors, and chronic diseases. For the economically active population (18-70 years, n = 14,041), the 12-month prevalence of occupational injuries was calculated with a 95% confidence interval (CI). Blockwise multiple logistic regression was applied to successively include different groups of variables. Overall, 2.8% (95% CI 2.4-3.2) of the gainfully employed population report at least one occupational injury (women: 0.9%; 95% CI 0.7-1.2; men: 4.3%; 95% CI 3.7-5.0). In the fully adjusted model, male gender (OR 3.16) and age 18-29 (OR 1.54), as well as agricultural (OR 5.40), technical (OR 3.41), skilled service (OR 4.24) or manual (OR 5.12), and unskilled service (OR 3.13) or manual (OR 4.97) occupations are associated with higher chances of occupational injuries. The same holds for frequent stressors such as heavy carrying (OR 1.78), working in awkward postures (OR 1.46), environmental stress (OR 1.48), and working under pressure (OR 1.41). Among health-related variables, physical inactivity (OR 1.47) and obesity (OR 1.73) present a significantly higher chance of occupational injuries. While the odds for most work-related factors were as expected, the associations for health-related factors such as smoking, drinking, and chronic diseases were rather weak. In part, this may be due to context-specific factors such as safety and workplace regulations in high-income countries like Germany. This assumption could guide further research, taking a multi-level approach to international comparisons.
Collapse
Affiliation(s)
- Alexander Rommel
- Robert Koch Institute, Epidemiology and Health Monitoring, General-Pape-Str. 62-66, 12101, Berlin, Germany
| | - Gianni Varnaccia
- Robert Koch Institute, Epidemiology and Health Monitoring, General-Pape-Str. 62-66, 12101, Berlin, Germany
| | - Nils Lahmann
- Charité-Universitätsmedizin Berlin, Institute of Health Sciences Education and Nursing, Augustenburger Platz 1, 13353, Berlin, Germany
| | - Jan Kottner
- Charité-Universitätsmedizin Berlin, Clinical Research Center for Hair and Skin Science, Charitéplatz 1, 10117, Berlin, Germany
| | - Lars Eric Kroll
- Robert Koch Institute, Epidemiology and Health Monitoring, General-Pape-Str. 62-66, 12101, Berlin, Germany
| |
Collapse
|