2022 International Conference on Life, Health and Modern Medicine
Bibliographic record
Abstract
LHMM001 AUTOMATED IDENTIFICATION AND QUANTIFICATION OF TRAUMATIC BRAIN INJURY FROM CT SCANS: ARE WE THERE YET? Atsuhiro Hibia, Majid Jaberipourb, Michael D. Cusimanoa,c, Alexander Bilbilyb,d, Rahul G. Krishnane,f, Richard I. Avivg, Pascal N. Tyrrella,b,h aInstitute of Medical Science, University of Toronto, Toronto, Ontario, Canada,bDepartment of Medical Imaging, University of Toronto, Toronto, Ontario, Canada,cDivision of Neurosurgery, St Michael’s Hospital, University of Toronto, Toronto, Canada,dSunnybrook Health Sciences Centre, Toronto, Canada,eDepartment of Computer Science, University of Toronto, Toronto, Ontario, Canada,fDepartment of Laboratory Medicine & Pathobiology, University of Toronto, Toronto, Ontario, Canada,gDepartment of Radiology, Radiation Oncology and Medical Physics, University of Ottawa, Ottawa, Ontario, Canada,hDepartment of Statistical Sciences, University of Toronto, Toronto, Ontario, Canada Objectives: The purpose of this study was to conduct a systematic review for understanding the availability and limitations of artificial intelligence (AI) approaches that could automatically identify and quantify CT findings in traumatic brain injury (TBI). Methods: Systematic review, in accordance with PRISMA 2020 and SPIRIT-AI extension guidelines, with a search of four databases (Medline, Embase, IEEE Xplore, and Web of Science) was performed to find AI studies that automated the clinical tasks for identifying and quantifying CT findings of TBI-related abnormalities. Results: A total of 531 unique publications were reviewed, which resulted in 66 articles that met our inclusion criteria. The following components for identification and quantification regarding TBI were covered and automated by existing AI studies: identification of TBI-related abnormalities; classification of intracranial hemorrhage types; slice-, pixel-, and voxel-level localization of hemorrhage; measurement of midline shift; and measurement of hematoma volume. Automated identification of obliterated basal cisterns was not investigated in the existing AI studies. Most of the AI algorithms were based on deep neural networks that were trained on two- or three-dimensional CT imaging datasets. Conclusions: We identified several TBI-related CT findings that can be automatically identified and quantified with AI. A combination of these techniques may provide useful tools to enhance reproducibility of TBI identification and quantification by supporting radiologists and clinicians in their TBI assessments and reducing subjective human factors. Acknowledgements This work was supported by a research grant from Nippon Steel Corporation (Fund Number 509533). LHMM002 ELECTRONIC PUBLIC HEALTH EMERGENCY MANAGEMENT (EPHEM): AN INNOVATIVE APPROACH FROM THE WHO EASTERN MEDITERRANEAN REGIONAL OFFICE Ali Abdullaha, Osman El Mahala, Huda Haidar Anana, Samar Hammouda, Dalia Samhouria aCountry Health Emergency Preparedness and International Health Regulations (CPI), World Health Organization Health Emergency Programme (WHE), World Health Organisation Regional Office for the Eastern Mediterranean (WHO EMRO), Cairo, Egypt. Background: Countries continue to establish and rely on Public Health Emergency Operation Centres (PHEOCs) to facilitate a well-coordinated, multi sectorial, all hazard public health emergency management process. An information management system is a core component of a functioning PHEOC. To that end, World Health Organization Eastern Mediterranean Regional Office (WHO EMRO) developed the electronic Public Health Emergency Management (ePHEM). In Phase 1, the Online Signals Module, within ePHEM, was piloted in the WHO regional office and at country level and proved its practicality and functionality where it enhanced Watch and Alert Modes operations within the PHEOC. Methods: A system analysis was conducted in order to identify the business requirements for the software through consultations with relevant technical experts in WHO and member states. A bi-regional meeting including both EMRO and African Regional Office (AFRO) with 34 countries participating resulted in building consensus and drafting the software’s business and functional requirements. The system prototype was developed (named ePHEM phase 1), modified and piloted in two settings, one at the regional office to support signal detection and management and one at PHEOC setting in Sudan to support the overall watch and alert functions of the PHEOC. Results: Through piloting ePHEM Phase 1, the signal management has improved significantly. Staff for the first time were able to remotely manage signals while working from home. Scope of information, signal management, triage process, verification process, division of labor, documentation, accountability, validation, communication, access to information, user experience, monitoring and evaluation and data analysis has all seen improvements using ePHEM. ePHEM Phase 2 is ready for piloting in countries, awaiting conclusion of Phase 1 pilots. Conclusions: Piloting ePHEM Phase 1 demonstrated the benefits of an online solution, enabling EMRO to remotely realize all Watch-Mode and Alert-Mode functions. Employing the software resulted in cleaner data, particularly when utilized by multiple users in addition to enforcing Standard Operational Procedures. Automated Dashboards assisted in decision making process. Available access to information improved overall awareness. A fitting tailored IT solution plays a key role in alertness, rapid decision making and response. LHMM003 COMMON TYPES OF UNREASONABLE MEDICAL ORDERS FOR INTRAVENOUS MEDICATION AND CONSTRUCTION OF INTERVENTION SYSTEM Xuan Lianga aThe 940th Hospital of Joint Logistic Support Force of Chinese People’s Liberation Army, Lanzhou, Gansu, 730000, China Background: This study aims to enhance pharmacists’ ability to review intravenous drug prescriptions or medical orders, standardize clinical intravenous medication, maximally avoid the safety risks in unreasonable intravenous drug prescriptions or medical orders, standardize drug allocation and delivery process, and improve the rationality in intravenous medication. Subjects and Methods: The unreasonable medical orders for intravenous medication in clinical practice were analyzed statistically, including drug concentration, dose, compatibility, inappropriate solvent, etc. Based on the workflow of “eight reviews and eight verifications,” the prescription was reviewed from 10 aspects of “drug concentration, dose, incompatibility, solvent, drug user, medication method, potential danger, whether skin test is needed, same drug with different drug name and drug name writing standard,” and verified from 10 aspects of “medical order, dispensing, drug division, warehouse entry, compatibility, warehouse exit, packaging, delivery, ward reception, and patient medication” to build the intervention system of “ten reviews and ten verifications.” Effort is needed to build information and feedback platform for intravenous clinical medication, strengthen the training of pharmacists’ professional ability to improve pharmacists’ intervention level and ability in clinical intravenous medication. Results: The level and quality of rational intravenous drug use in hospitals are significantly improved, and unreasonable medical orders and irrational prescriptions before drug use are maintained a level of less in Conclusions: The “ten reviews and ten intervention system for intravenous medication maximally irrational drug prescription or unreasonable medical orders, the patient safety in intravenous medication, and for the safety of intravenous medication in OF OF of Science, of & of & University of and to this Background: This study through on in and the and by which with it is to and the and health of and provide a for reducing through a of to the and not for a it a on it is to to Subjects and Methods: from a in China and by to the for and were from the of with and were and while that was the same in the two with two the and the and for an and the use to test the and the and the test Results: in are in and are in the level of and can which a role in the and of Conclusions: strengthen the health and of different different and conduct health to the and of at different strengthen health for and in this to to the of and the test data that can a in the and a which has The the 2020 on the and of the in in the OF THE OF AND aThe Hospital of China To study the of on the of and Methods: were for the is with the is with was for for and the were for test by The was a the the were the The were in or in the of and both and the were data were analyzed using data analysis of with test using test and test and were performed using data using the test were Results: that the of significantly in the the was not different from the and the of the was The and were to the and the of was significantly the which was that the the can improve the and the improve the the can be significantly improved when with OF OF AND AND OF aInstitute of of Background: is a We the of intervention on and ability of and the of and in the and of and ability of by Subjects and Methods: In the were to with of and were using the and the of and in the was using and Results: The of the platform was in the which in was that in the same the of platform of in was significantly that in and the of platform of in was significantly that in The of in was significantly that in with the of and in were significantly The of in of was that of the was not and the was The of total in of was significantly of and in were significantly in The of in was significantly that in and the was that in with the of in was significantly Conclusions: The and of and and intervention for can and the of and ability in by and and This work was supported by a grant from a of OF THE MEDICATION OF THE OF Hospital, Hospital To the of Chinese in the of based on Methods: from the of the of and Chinese to 1, were The in the and information of the are to establish a on the of prescription and the and of the was for systematic The in performed analysis and a Results: articles were including 66 Chinese of with a of of are 10 in which was The with the were and of the of are of with the for by for and for drug were the were were and for analysis of Chinese of were analysis of Chinese of drug were including the to the and the and and and of on the and on the and and AND HEALTH OF of China Background: with the of and is to public and etc. to and and the of health and ability has and To the ability and health of in different in the for this Subjects and Methods: In this and with an of 10 The and 1 The test were with the of the same in the Results: The that the and of the were significantly the The of was and their was while the of was and their was The and ability were significantly the The of was and that of was is the and is the The is the The of was the and was the Conclusions: by regional and the of and of the was significantly the in a of in their which is for the of and This work was supported by of and Sciences IDENTIFICATION AND OF Hospital, Hospital Management China To the identification of through the deep neural to and Methods: The by the were data The were and to of the data were the training the test and the the conduct data build the data to the classification identification the data are two to the identification in the and the two with the to the identification time and The identification of the classification and identification was and the was and the was and and the was and The identification was and the total time was The time of the identification was use time of The of and in was and The time is The total time is In the The of and professional in was The time is time of The by has in and which can be for and of Acknowledgements on the and and in with Health of OF FOR OF aInstitute of and Hospital for and Health of of and of of Science, Hospital of University of Chinese Laboratory of of of and Health of and to this Background: a role in the of the This study at the of the with two of of on the of Subjects and Methods: A total of with were to four and in a the of the were analyzed using the Results: with that these two and both the and of the The analysis demonstrated that a on the the four of the functional approaches that the while the and level in the In the were in the Conclusions: findings demonstrated that with or could the and in the of This research was supported in by from the and and of and OF THE OF AND OF THE MEDICAL of University of Chinese of University of Chinese Background: To use to of evaluation and of Chinese and of the of with the purpose of and and medical Subjects and Methods: This to use software to the of with and to use Chinese and to provide from the aspects of of and of platform of core and the of the the and the evaluation method, the and the In the of was conducted the and subjective and evaluation was conducted on the of the of Chinese and and the of Results: A total of were were and the was The evaluation was in the that the could for the of and the a of in understanding of Chinese and and systematic ability of medical and of In of and the of was and The subjective evaluation investigated two of the that were the and the aspects to be improved, and that the of the were understanding of and The are the of the of and the of The and of this can for the of to the of online in the of and provide a for the of a system of and to the training of and medical in the This work was supported by The first of and of the of in of and of in and of the of and Medicine in and of the of THE A People’s Hospital, Hospital of the Chinese University of and to this Background: the of of 2 has for public health and practice in to be the time of and to 10 in and in and The with is from Based on the use of and for the of with not Subjects and Methods: The purpose of this study was to and the clinical for regarding to the time and to identify the management of the Methods: in People’s Hospital of were to were for using the total from through the of and by the were with and with and Results: the in the were in were were were and the and in and and not in and time test was was these regarding the whether were with and or Conclusions: We that the time of is a which has not with of and the drug This work was supported by the for of Public of Chinese of Medical Sciences and Medical and Health and of Chinese of Medical Sciences, Medical and Medical and Health THE OF FOR of of Background: for with on the of and for with at the of the and level of with through the and research of the training of training for the and of Subjects and Methods: on the of the of professional in A of and in the of training to improve the quality of professional from and a for the of with the combination of health and Results: The training quality of has improved by has a training of and for professional a system for professional the of professional of a of and and in and the of health for has to Conclusions: The for and for is and the training of is the that in the with the of and are the of training in the In the of professional based on with with and their the of is and and the of for with with and their is the of professional The and and the of professional are to the of training and of This research was supported by a grant The and of by the of in OF PUBLIC HEALTH HEALTH of Public Medical Hospital, Medical China Background: The is and a Public Health Emergency of International to a to the professional of on health evaluation and to research whether the professional of are on the is that of are not on the the are the of the of the the and are by the the work of the is not by in a of professional be on their health in of the professional of Methods: In this the in professional in and hospitals were investigated through a in two public hospitals in Hospital a total of including and Hospital a total of including and A and the were to professional of analysis and multiple were to research whether in improved professional the analyzed and in and whether the was on the or not on their and Results: was of in the of with on the professional of in this and the professional in In multiple professional in all and different professional or not to in the of the not on the professional was an in the of the the with to be in to on the health of Acknowledgements on the and to the of the and China OF THE OF FOR AN Michael Pascal N. aInstitute of Medical Science, University of Toronto, Canada,bDepartment of Radiology, Hospital of Medical Imaging, University of Toronto, of Computer Science, University of Toronto, Canada,eDepartment of Statistical Sciences, University of Toronto, Background: on is by the artificial intelligence (AI) to the availability of data for is a that can be and quality of in the to and Automated detection of using can time to to the and improve quality of data has a solution for the availability of for AI to the of in the is a Methods: This study a artificial of to the of a A was trained using networks Results: the in and our in the of and the limitations of a were using a human and training a classification and an overall of to using the and based on two Conclusions: The use of our an in AI training to data AI research in the study of and the of AI in This work was supported by OF OF of and Sciences, China Background: a is two and is a with and a plays an role in the of To study the of from on in Subjects and Methods: The were with and for one in the with were with were the were and the from and was to the Results: The of the was a the the of the was the of total and the from a on the of in Conclusions: The data that the of a on is to the in data provide data for and provide research for the of health based on This research supported by of China A FOR HEALTH PUBLIC HEALTH of Background: A public health which has and in a to human and safety and Subjects and Methods: using the of and this an and research on the of public health the emergency by and the use of and to the of in to health and Results: The is a and can In the of the of the in addition to and to in a it is to strengthen their through can improve the system of the human health to the of Conclusions: and are at a of and is to strengthen the health in and and to strengthen the of in order to the and of and and using the and at 1 of and the of THE OF and University of University of and China Background: has a all the the of the of developed countries, this is an of the of and and the of In the the of the continue to and a on the of and not to the of the the of the and the of the for medical and In is a to with and is to to the of in the of Subjects and Methods: The of the the and health of the the one the of for the is to improve the quality of the and of the the it can with and with the in time before medical and their the and this to the of in the of for the and of the and Results: of were analyzed in the research process, and it was that a role in with by to with the of the through the of to the Conclusions: The of the is the in of and the is which the of the OF INNOVATIVE HEALTH FOR THE OF of & Background: to health the of the of is a of and is a to the of the of Subjects and Methods: In order to the of to conduct an analysis of health for which is of and Based on the existing and this study reviews the on health and working of and of the of the Results: In health and a of and in China conducted and and studies on the of health and and of which the of research on health in the of and all aspects of and and has the it is that the research is are research in for the following the research in the of health is the method, and the study method, method, analysis method, and research are for of the the health of a of and of the the health of a of and the two are two work of and the is not Conclusions: Health and a and to build on this to health and and in our This work was to for and in work and A THE OF INTERVENTION FOR of of China Background: is a that the to enhance and and is a with which the combination of and and and is not a of the to are an intervention to the of with to and the and the to training in to and of the in a and Subjects and Methods: To the of on the of with and to provide for the of of with with from a in were and were an intervention and a The intervention a and the maintained the and the the was to test the two of The total the in the of the Results: the was in the of the intervention and the the the of the intervention and the were significantly different the intervention in the In the of in all aspects before and was in and of while the four aspects in the before and intervention In the of in all the and the total were significantly different and was in the four aspects Conclusions: can brain and improve the of with FOR FOR MEDICAL FROM THE OF of China Background: The of may to with human and The medical be and to medical In the of is from the of the of the in this was and relevant and were The of and was and the on the of the Subjects and Methods: The of medical is an of which are with technical and that to be This the of in the and that the for has in the and that are in the of by in the to for medical for The the of for medical and that a of to avoid medical Results: The of to avoid medical for is including the the practice by the to the and with the of and use of Conclusions: In the of the avoid the of medical from Based on the analysis of the and of medical in the of this for to avoid the of medical from a to that can avoid the of medical to the based on the safety of clinical medical HEALTH OF THE of University of and of University China Background: Based on the research of safety of in the of safety is not the of the was not in including The of can be by and to the the a it to with a of the study was conducted to the level of and the health of to and Subjects and Methods: software to the for the of in based on different The hazard in the were analyzed two were and The and was regarding on the and of the to the and different a is to these and to the of human health and of by to Results: the of and injury with the of the injury with the of the and to be at the same concentration, the of is that of and the is that of Conclusions: from the using software to the be the first the of and to the safety of that the health of to was the by and management to and the to an including of and one of the for the of the is for the of the AND FOR AND THE PUBLIC HEALTH EMERGENCY of and of and of of and China Background: The public health emergency that has the has a on and to and to emergency public health and has a for the all the and are to be the and to and the Subjects and Methods: the is to different the for that a and is to the to support or based on the the total or is of two the and the the which could the potential to the of the The the total and is Results: The for by the different of which by of & is the is or to is is This that can not the is the one for the significantly with the is the one for the total with the the total
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.193 | 0.067 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".