Quantitative assessment of the impact of a triage physician on the Accreditation Council for Graduate Medical Education resident milestones in the emergency department

The “door-to-doctor” time for patients to be seen by a physician is an increasingly studied metric.Hospitals may shorten this time by implementing a triage physician (TP).The exact role of a TP may vary across departments.TPs put in preliminary orders for lab work,imaging,and treatment,and decide treatment location for further evaluation.As the prevalence of TPs grows,its effect on resident education in academic emergency departments (EDs) remains unclear.We implemented a TP in the spring of 2016 and assessed resident physicians before and after implementation.

Computer vision-aided DEM study on the compaction characteristics of graded subgrade filler considering realistic coarse particle shapes

The compaction quality of subgrade filler strongly affects subgrade settlement.The main objective of this research is to analyze the macro-and micro-mechanical compaction characteristics of subgrade filler based on the real shape of coarse particles.First,an improved Viola-Jones algorithm is employed to establish a digitalized 2D particle database for coarse particle shape evaluation and discrete modeling purposes of subgrade filler.Shape indexes of 2D subgrade filler are then computed and statistically analyzed.Finally,numerical simulations are performed to quantitatively investigate the effects of the aspect ratio(AR)and interparticle friction coefficient(μ)on the macro-and micro-mechanical compaction characteristics of subgrade filler based on the discrete element method(DEM).The results show that with the increasing AR,the coarse particles are narrower,leading to the increasing movement of fine particles during compaction,which indicates that it is difficult for slender coarse particles to inhibit the migration of fine particles.Moreover,the average displacement of particles is strongly influenced by the AR,indicating that their occlusion under power relies on particle shapes.The dis-placement and velocity of fine particles are much greater than those of the coarse particles,which shows that compaction is primarily a migration of fine particles.Under the cyclic load,the interparticle friction coefficientμhas little effect on the internal structure of the sample;under the quasi-static loads,however,the increase inμwill lead to a significant increase in the porosity of the sample.This study could not only provide a novel approach to investigate the compaction mechanism but also establish a new theoretical basis for the evaluation of intelligent subgrade compaction.

Computerized tomography-guided therapeutic percutaneous puncture catheter drainage-combined with somatostatin for severe acute pancreatitis: An analysis of efficacy and safety

BACKGROUND Severe acute pancreatitis(SAP),a condition with rapid onset,critical condition and unsatisfactory prognosis,poses a certain threat to human health,warranting optimization of relevant treatment plans to improve treatment efficacy.AIM To evaluate the efficacy and safety of computerized tomography-guided the-rapeutic percutaneous puncture catheter drainage(CT-TPPCD)combined with somatostatin(SS)in the treatment of SAP.METHODS Forty-two SAP patients admitted to The Second Affiliated Hospital of Fujian Medical University from June 2020 to June 2023 were selected.On the basis of routine treatment,20 patients received SS therapy(control group)and 22 patients were given CT-TPPCD plus SS intervention(research group).The efficacy,safety(pancreatic fistula,intra-abdominal hemorrhage,sepsis,and organ dysfunction syndrome),abdominal bloating and pain relief time,bowel recovery time,hospital stay,inflammatory indicators(C-reactive protein,interleukin-6,and pro-calcitonin),and Acute Physiology and Chronic Health Evaluation(APACHE)II score of both groups were evaluated for comparison.RESULTS Compared with the control group,the research group had a markedly higher total effective rate,faster abdominal bloating and pain relief and bowel recovery,INTRODUCTION Pancreatitis,an inflammatory disease occurring in the pancreatic tissue,is classified as either acute or chronic and is associated with high morbidity and mortality,imposing a socioeconomic burden[1,2].The pathogenesis of this disease involves early protease activation,activation of nuclear factor kappa-B-related inflammatory reactions,and infiltration of immune cells[3].Severe acute pancreatitis(SAP)is a serious condition involving systemic injury and subsequent possible organ failure,accounting for 20%of all acute pancreatitis cases[4].SAP is also characterized by rapid onset,critical illness and unsatisfactory prognosis and is correlated with serious adverse events such as systemic inflammatory response syn-drome and acute lung injury,threatening the health of patients[5,6].Therefore,timely and effective therapeutic inter-ventions are of great significance for improving patient prognosis and ensuring therapeutic effects.Somatostatin(SS),a peptide hormone that can be secreted by endocrine cells and the central nervous system,is in-volved in the regulatory mechanism of glucagon and insulin synthesis in the pancreas[7].It has complex and pleiotropic effects on the gastrointestinal tract,which can inhibit the release of gastrointestinal hormones and negatively modulate the exocrine function of the stomach,pancreas and bile,while exerting a certain influence on the absorption of the di-gestive system[8,9].SS has shown certain clinical effectiveness when applied to SAP patients and can regulate the severity of SAP and immune inflammatory responses,and this regulation is related to its influence on leukocyte apoptosis and adhesion[10,11].Computerized tomography-guided therapeutic percutaneous puncture catheter drainage(CT-TPPCD)is a surgical procedure to collect lesion fluid and pus samples from necrotic lesions and perform puncture and drainage by means of CT image examination and precise positioning[12].In the research of Liu et al[13],CT-TPPCD applied to pa-tients undergoing pancreatic surgery contributes to not only good curative effects but also a low surgical risk.Baudin et al[14]also reported that CT-TPPCD has a clinical success rate of 64.6%in patients with acute infectious necrotizing pan-creatitis,with nonfatal surgery-related complications found in only two cases,suggesting that this procedure is clinically effective and safe in the treatment of the disease.In light of the limited studies on the efficacy and safety of SS plus CT-TPPCD in SAP treatment,this study performed a relevant analysis to improve clinical outcomes in SAP patients.

Evaluation of hand infections in the emergency department using point-of-care ultrasound

BACKGROUND:We aimed to evaluate the utility of point-of-care ultrasound(POCUS)in the assessment of hand infections that present to the emergency department(ED)and its impact on medical decision making and patient management.METHODS:We conducted a retrospective review of patients who presented to two urban academic EDs with clinical presentations concerning for skin and soft tissue infections(SSTI)of the hand between December 2015 and December 2021.Two trained POCUS fellowship physicians reviewed an ED POCUS database for POCUS examinations of the hand.We then reviewed patients’electronic health records(EHR)for demographic characteristics,history,physical examination findings,ED course,additional imaging studies,consultations,impact of POCUS on patient care and final disposition.RESULTS:We included a total of 50 cases(28 male,22 female)in the final analysis.The most common presenting symptoms and exam findings were pain(100%),swelling(90%),and erythema(74%).The most common sonographic findings were edema(76%),soft tissue swelling(78%),and fluid surrounding the tendon(57%).POCUS was used in medical decision making 68%of the time(n=34),with the use of POCUS leading to changes in management 38%of the time(n=19).POCUS use led to early antibiotic use(11/19),early consultation(10/19),and led to the performance of a required procedure(8/19).The POCUS diagnosis was consistent with the discharge diagnosis of flexor tenosynovitis 8/12 times,abscess 12/16 times,and cellulitis 14/20 times.CONCLUSION:POCUS is beneficial for evaluating of hand infections that present to the ED and can be used as an important part of medical decision making to expedite patient care.

Early Detection of Colletotrichum Kahawae Disease in Coffee Cherry Based on Computer Vision Techniques

Colletotrichum kahawae(Coffee Berry Disease)spreads through spores that can be carried by wind,rain,and insects affecting coffee plantations,and causes 80%yield losses and poor-quality coffee beans.The deadly disease is hard to control because wind,rain,and insects carry spores.Colombian researchers utilized a deep learning system to identify CBD in coffee cherries at three growth stages and classify photographs of infected and uninfected cherries with 93%accuracy using a random forest method.If the dataset is too small and noisy,the algorithm may not learn data patterns and generate accurate predictions.To overcome the existing challenge,early detection of Colletotrichum Kahawae disease in coffee cherries requires automated processes,prompt recognition,and accurate classifications.The proposed methodology selects CBD image datasets through four different stages for training and testing.XGBoost to train a model on datasets of coffee berries,with each image labeled as healthy or diseased.Once themodel is trained,SHAP algorithmto figure out which features were essential formaking predictions with the proposed model.Some of these characteristics were the cherry’s colour,whether it had spots or other damage,and how big the Lesions were.Virtual inception is important for classification to virtualize the relationship between the colour of the berry is correlated with the presence of disease.To evaluate themodel’s performance andmitigate excess fitting,a 10-fold cross-validation approach is employed.This involves partitioning the dataset into ten subsets,training the model on each subset,and evaluating its performance.In comparison to other contemporary methodologies,the model put forth achieved an accuracy of 98.56%.

Emergency department management of acute agitation in the reproductive age female and pregnancy

BACKGROUND:Agitation is a common presentation within emergent departments(EDs).Agitation during pregnancy should be treated as an obstetric emergency,as the distress may jeopardize both the patient and fetus.The safety of psychotropic medications in the reproductive age female has not been well established.This review aimed to explore a summary of general agitation recommendations with an emphasis on ED management of agitation during pregnancy.METHODS:A literature review was conducted to explore the pathophysiology of acute agitation and devise a preferred treatment plan for ED management of acute agitation in the reproductive age or pregnant female.RESULTS:While nonpharmacological management is preferred,ED visits for agitation often require medical management.Medication should be selected based on the etiology of agitation and the clinical setting to avoid major adverse effects.Adverse effects are common in pregnant females.For mild to moderate agitation in pregnancy,diphenhydramine is an effective sedating agent with minimal adverse effects.In moderate to severe agitation,high-potency typical psychotropics are preferred due to their neutral effects on hemodynamics.Haloperidol has become the most frequently utilized psychotropic for agitation during pregnancy.Second generation psychotropics are often utilized as second-line therapy,including risperidone.Benzodiazepines and ketamine have demonstrated adverse fetal outcomes.CONCLUSION:While randomized control studies cannot be ethically conducted on pregnant patients requiring sedation,animal models and epidemiologic studies have demonstrated the effects of psychotropic medication exposure in utero.As the fetal risk associated with multiple doses of psychotropic medications remains unknown,weighing the risks and benefits of each agent,while utilizing the lowest effective dose remains critical in the treatment of acute agitation within the EDs.

Evaluation of disease burden and symptom scores in patients with acute atrial fi brillation in the emergency department

Atrial fibrillation(AF)is a major public health problem and poses a substantial economic burden on healthcare systems worldwide.[1-4]The emergency department(ED)serves as the first point of contact with the healthcare system and plays a key role in the management of patients with AF,which accounts for 3%-10%of all hospital admissions.[5]Treatment plans are often discussed and initiated at the ED.

Early endotracheal intubation is not associated with the rate of return of spontaneous circulation following cardiac arrest at the emergency department:an exploratory analysis

Cardiac arrest poses a significant global public health challenge,manifesting in approximately 550,000 cases annually within the United States.[1]In-hospital cardiac arrest(IHCA)is commonly attributed to airways and respiratory issues.[2]Recommendations emphasize the expertise of responders in airway management.[3]Various options exist,such as chest compression-only cardiopulmonary resuscitation(CPR),bag-mask ventilation(BMV),and advanced airways.The BMV and advanced airways are not deemed equivalent or superior based on previous evidence.[4]Achieving consistency in choosing and timing the optimal airway approach during IHCA is crucial.The current American Heart Association guidelines suggest an advanced airway strategy when endotracheal intubation(ETI)success rates are high,but the optimal time for advanced airway management remains unclear.[5]Wong et al[6]revealed that survival improved by less than 5 min with advanced airway management.According to a subgroup analysis of IHCA patients in emergency departments(EDs),early intubation was associated with a 1.5-fold greater rate of return of spontaneous circulation(ROSC)than in other locations.[7]ED patients’constant monitoring and immediate management,with readily available intubation equipment,enhance early intubation and survival rates.[6]Nonetheless,IHCA patients intubated within the first 15 min had a lower ROSC rate.

Diagnostic efficacy of virtual organ computer-assisted analysis in measuring the volume ratio of subchorionic hematoma with serum progesterone

BACKGROUND Subchorionic hematoma(SCH)is a common complication in early pregnancy characterized by the accumulation of blood between the uterine wall and the chorionic membrane.SCH can lead to adverse pregnancy outcomes such as miscarriage,preterm birth,and other complications.Early detection and accurate assessment of SCH are crucial for appropriate management and improved pregnancy outcomes.AIM To evaluate the diagnostic efficacy of virtual organ computer-assisted analysis(VOCAL)in measuring the volume ratio of SCH to gestational sac(GS)combined with serum progesterone on early pregnancy outcomes in patients with SCH.METHODS A total of 153 patients with SCH in their first-trimester pregnancies between 6 and 11 wk were enrolled.All patients were followed up until a gestational age of 20 wk.The parameters of transvaginal two-dimensional ultrasound,including the circumference of SCH(Cs),surface area of SCH(Ss),circumference of GS(Cg),and surface area of GS(Sg),and the parameters of VOCAL with transvaginal three-dimensional ultrasound,including the three-dimensional volume of SCH(3DVs)and GS(3DVg),were recorded.The size of the SCH and its ratio to the GS size(Cs/Cg,Ss/Sg,3DVs/3DVg)were recorded and compared.RESULTS Compared with those in the normal pregnancy group,the adverse pregnancy group had higher Cs/Cg,Ss/Sg,and 3DVs/3DVg ratios(P<0.05).When 3DVs/3DVg was 0.220,the highest predictive performance predicted adverse pregnancy outcomes,resulting in an AUC of 0.767,and the sensitivity,specificity were 70.2%,75%respectively.VOCAL measuring 3DVs/3DVg combined with serum progesterone gave a diagnostic AUC of 0.824 for early pregnancy outcome in SCH patients,with a high sensitivity of 82.1%and a specificity of 72.1%,which showed a significant difference between AUC.CONCLUSION VOCAL-measured 3DVs/3DVg effectively quantifies the severity of SCH,while combined serum progesterone better predicts adverse pregnancy outcomes.

Multidetector computer tomography and magnetic resonance imaging of double superior mesenteric veins:A case report

BACKGROUND This study aimed to describe the findings of double superior mesenteric veins(SMVs),a rare anatomical variation,on multidetector computer tomography(MDCT)and magnetic resonance imaging(MRI)images.CASE SUMMARY We describe the case of a 34-year-old male,who underwent both MDC and MRI examinations of the upper abdomen because of liver cirrhosis.MDCT and MRI angiography images of the upper abdomen revealed an anatomic variation of the superior mesenteric vein(SMV),the double SMVs.CONCLUSION The double SMVs are a congenital abnormality without potential clinical manifestation.Physicians need to be aware of this anatomical variation during abdominal surgery to avoid iatrogenic injury.

Laboratory or Department?Exploration and Creation in Computer Science and Technology

In the very beginning,the Computer Laboratory of the University of Cambridge was founded to provide computing service for different disciplines across the university.As computer science developed as a discipline in its own right,boundaries necessarily arose between it and other disciplines,in a way that is now often detrimental to progress.Therefore,it is necessary to reinvigorate the relationship between computer science and other academic disciplines and celebrate exploration and creativity in research.To do this,the structures of the academic department have to act as supporting scaffolding rather than barriers.Some examples are given that show the efforts being made at the University of Cambridge to approach this problem.

Optimizing Deep Learning for Computer-Aided Diagnosis of Lung Diseases: An Automated Method Combining Evolutionary Algorithm, Transfer Learning, and Model Compression

Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.

Congenital Heart Disease Referred for Surgery: Analysis and Epidemiological Description in the Cardiology Department of CHU Ignace Deen

Introduction: Congenital heart disease includes all cardiac and vascular malformations. It accounts for approximately one third of all congenital malformations and is a public health problem, particularly in developing countries. The aim of this study was to analyze the epidemiological, clinical and paraclinical aspects of congenital heart disease. Methods: This was a retrospective descriptive and analytical study based on the records of 135 patients referred for surgery and followed up in the cardiology department of the Ignace Deen University Hospital, collected in November 2022. Results: Hospital prevalence was 5%. The mean age was 71 months, ranging from 1 month to 19 years. The age group over 24 months was the most represented (62%). The M/F sex ratio was 1.36. Urban origin was predominant (58%). The rate of children not attending school or dropping out was high (16%). Siblings with fewer than 4 children were the most common (88%). A heart murmur was the most frequent sign (78%), followed by cyanosis (36%) and heart failure (29%). The association between heart murmurs and CHD was proven with a p-value Conclusion: CHDs represent the main indication for paediatric cardiac surgery and follow-up (95%). We stress the importance of implementing a screening and management strategy for congenital heart disease.

Study on sex differences and potential clinical value of threedimensional computerized tomography pelvimetry in rectal cancer patients

BACKGROUND Laparoscopic rectal cancer radical surgery is a complex procedure affected by various factors.However,the existing literature lacks standardized parameters for the pelvic region and soft tissues,which hampers the establishment of consistent conclusions.AIM To comprehensively assess 16 pelvic and 7 soft tissue parameters through computerized tomography(CT)-based three-dimensional(3D)reconstruction,providing a strong theoretical basis to address challenges in laparoscopic rectal cancer radical surgery.METHODS We analyzed data from 218 patients who underwent radical laparoscopic surgery for rectal cancer,and utilized CT data for 3D pelvic reconstruction.Specific anatomical points were carefully marked and measured using advanced 3D modeling software.To analyze the pelvic and soft tissue parameters,we emp-loyed statistical methods including paired sample t-tests,Wilcoxon rank-sum tests,and correlation analysis.RESULTS The investigation highlighted significant sex disparities in 14 pelvic bone parameters and 3 soft tissue parameters.Males demonstrated larger measurements in pelvic depth and overall curvature,smaller measurements in pelvic width,a larger mesorectal fat area,and a larger anterior-posterior abdominal diameter.By contrast,females exhibited wider pelvises,shallower depth,smaller overall curvature,and an increased amount of subcutaneous fat tissue.However,there were no significant sex differences observed in certain parameters such as sacral curvature height,superior pubococcygeal diameter,rectal area,visceral fat area,waist circumference,and transverse abdominal diameter.CONCLUSION The reconstruction of 3D CT data enabled accurate pelvic measurements,revealing significant sex differences in both pelvic and soft tissue parameters.This study design offer potential in predicting surgical difficulties and creating personalized surgical plans for male rectal cancer patients with a potentially“difficult pelvis”,ultimately improving surgical outcomes.Further research and utilization of these parameters could lead to enhanced surgical methods and patient care in laparoscopic rectal cancer radical surgery.

Reliability of a computerized system for strabismus screening

AIM:To evaluate the reliability of Photo-Hirschberg screening for global strabismus performed by non-specialized personnel.METHODS:Participants at three sites were enrolled.One person at each site was trained in visual acuity measurement and use of the computerized system.Visual acuity was measured,and strabismus testing was performed using two flash photographs.All data from the three primary observers were sent to an experienced assistant researcher,who was blinded to the primary results,for re-evaluation.The primary and re-evaluation results of the Photo-Hirschberg screenings using weighted kappa for agreement were compared.RESULTS:The study included 181 participants(88 males and 93 females)and the results for primary and re-evaluation screenings were corresponded.Ten participants with contrasting results presented with unclear corneal light reflex.Sensitivity and specificity were 100%[95%confidence interval(CI):29.0%-100%]and 99.4%(95%CI:96.6%-100%),respectively,based on the Agresti test of the primary evaluation,considering the re-evaluated classification as true.CONCLUSION:The computerized system can be used for primary strabismus screening by non-specialized personnel,with 98.8%agreement with specialists.However,it cannot be used as a substitute for professional examination.

Avoiding misdiagnosis of multilocular thymic cysts as malignant tumors on computer tomography

This editorial provides insights from a case report by Sun et al published in the World Journal of Clinical Cases.The case report focuses on a case where a multilocular thymic cyst(MTC)was misdiagnosed as a thymic tumor,resulting in an unnecessary surgical procedure.Both MTCs and thymic tumors are rare conditions that heavily rely on radiological imaging for accurate diagnosis.However,the similarity in their imaging presentations can lead to misinterpretation,resulting in unnecessary surgical procedures.Due to the ongoing lack of comprehensive knowledge about MTCs and thymic tumors,we offer a summary of diagnostic techniques documented in recent literature and examine potential causes of misdiagnosis.When computer tomography(CT)values surpass 20 Hounsfield units and display comparable morphology,there is a risk of misdiagnosing MTCs as thymic tumors.Employing various differential diagnostic methods like biopsy,molecular biology,multi-slice CT,CT functional imaging,positron emission tomography/CT molecular functional imaging,magnetic resonance imaging and radiomics,proves advantageous in reducing clinical misdiagnosis.A deeper understanding of these conditions requires increased attention and exploration by healthcare providers.Moreover,the continued advancement and utilization of various diagnostic methods are expected to enhance precise diagnoses,provide appropriate treatment options,and improve the quality of life for patients with thymic tumors and MTCs in the future.continued advancement and utilization of various diagnostic methods are expected to enhance precise diagnoses,provide appropriate treatment options,and improve the quality of life for patients with thymic tumors and MTCs in the future.

Echocardiographic Aspects of Type 2 Diabetics Patients Hospitalized in the Medicine and Endocrinology Department of the Mali Hospital

Introduction: Cardiovascular disease is the leading cause of death in diabetics. The objective of our study was to investigate the echocardiographic aspects of type 2 diabetics. Patients and Method: Descriptive and cross-sectional study of 12 months from June 2020 to June 2021. We included hospitalized type 2 diabetics who underwent transthoracic cardiac ultrasound in the Department of Medicine and Endocrinology at the Mali Hospital. Results: We collected 128 type 2 diabetics. The predominance was male with a sex ratio of 1.2. The mean age of patients was 60.06 ± 11.54 years with extremes of 28 and 84 years. Echocardiographic abnormalities were dominated by abnormal relaxation of left ventricle in 62.5%, increased of left ventricle mass in 54.7% and left atrium dilation in 28.1%. Patients with type 2 diabetes mellitus and hypertension had more left atrium dilation with a p of 0.02. Disorders of global kinetics and systolic dysfunction were more prevalent in smoking patients with statistically significant associations, respectively, p = 0.02;p = 0.03. Dyslipidemia had a statistically significant association with segmental kinetic disorders with a p of 0.008. Duration of diabetes greater than 5 years was associated with left atrium dilation and p-value was 0.04. Conclusion: Diabetes is responsible for cardiovascular manifestations that can be identified with transthoracic echocardiography. Its performance in diabetic patients makes it possible to refine the patient’s management.

Therapeutic Compliance of Hypertensive Patients Followed in Ambulatory in the Cardiology Department of Kati University Hospital

Introduction: High blood pressure is a major public health problem worldwide due to its frequency and cardiovascular complications. Adherence to treatment for chronic diseases is a global problem. The aim was to study therapeutic adherence in hypertensive patients followed in ambulatory. Materials and Methods: This was a cross-sectional, descriptive study with prospective recruitment that took place from July 1 to December 31, 2022 (6 months) in the cardiology department of the university hospital of Kati. The variables studied were sociodemographic data, cardiovascular risk factors, comorbidities, the possession of insurance and compliance (the Girerd questionnaire was used to assess adherence). Results: A total of 1182 patients were consulted, including 887 for hypertension, a frequency of 75%. Fifty-six patients were included in the study. The average age was 58.18 ± 13.25 years with extremes of 30 and 80 years. There was a female predominance (75%) with a sex ratio of 0.3. The majority of patients lived in urban areas (89.3%). Out-of-school patients accounted for 44.6%, more than half of patients or 55.4% had no income, patients with medical coverage accounted for 67.9% of cases. The main risk factors were physical inactivity (25%) followed by smoking 14.3%. More than 71% of patients had a compliance problem and the main reasons were forgetting to take the drug with 73.2%, followed by delayed treatment of 50% and drug discontinuation of 28.6%. Conclusion: Compliance is a real challenge and a major public health issue. This study allowed us to find a real problem of compliance in our hypertensive patients. There was a statistically significant relationship between drug adherence and forgetting to take the drug and drug discontinuation.

Prediction of sepsis within 24 hours at the triage stage in emergency departments using machine learning

BACKGROUND:Sepsis is one of the main causes of mortality in intensive care units(ICUs).Early prediction is critical for reducing injury.As approximately 36%of sepsis occur within 24 h after emergency department(ED)admission in Medical Information Mart for Intensive Care(MIMIC-IV),a prediction system for the ED triage stage would be helpful.Previous methods such as the quick Sequential Organ Failure Assessment(qSOFA)are more suitable for screening than for prediction in the ED,and we aimed to fi nd a light-weight,convenient prediction method through machine learning.METHODS:We accessed the MIMIC-IV for sepsis patient data in the EDs.Our dataset comprised demographic information,vital signs,and synthetic features.Extreme Gradient Boosting(XGBoost)was used to predict the risk of developing sepsis within 24 h after ED admission.Additionally,SHapley Additive exPlanations(SHAP)was employed to provide a comprehensive interpretation of the model's results.Ten percent of the patients were randomly selected as the testing set,while the remaining patients were used for training with 10-fold cross-validation.RESULTS:For 10-fold cross-validation on 14,957 samples,we reached an accuracy of 84.1%±0.3%and an area under the receiver operating characteristic(ROC)curve of 0.92±0.02.The model achieved similar performance on the testing set of 1,662 patients.SHAP values showed that the fi ve most important features were acuity,arrival transportation,age,shock index,and respiratory rate.CONCLUSION:Machine learning models such as XGBoost may be used for sepsis prediction using only a small amount of data conveniently collected in the ED triage stage.This may help reduce workload in the ED and warn medical workers against the risk of sepsis in advance.

Diabetic Macroangioapathy at the Internal Medicine Department of the Abass Ndao Hospital Center (About 359 Cases)

Introduction: Macroangiopathy plays an important role, with a high prevalence of morbidity and mortality in diabetic patients. The aim was to study the epidemiological, clinical, paraclinical, therapeutic and evolutionary profile of macroangiopathy in diabetic patients in the internal medicine department of the Abass Ndao hospital. Patients and methods: This was a descriptive and analytical cross-sectional study. Our investigations were recruited over a 7-year period (January 1, 2016 to December 31, 2022). Results: Three hundred and fifty-nine (359) patients (10.22%) were enrolled. The mean age was 62.83 years, with extremes ranging from 17 to 98 years. The [60 - 69] age group was more representative (37.32%). Women accounted for 180 cases (50.1%), with a sex ratio (m/f) of 0.99. The average duration of diabetes was 11.86 years. Average consultation time was 38.07 days, with extremes ranging from 1 to 368 days. Average hospital stay was 7.65 days. Inaugural diabetes was noted in 12 cases (3.34%). Type 2 diabetes accounted for 95.82% (n = 344) of patients. Hypertension was present in 150 patients (41.8%). Patients with 2 risk factors accounted for 173 cases (48.18%). Nineteen patients had already had a stroke (5.29% of cases). Fourteen (14) patients (4.2%) were amputees. Obliterative arteriopathy of the lower limbs (AOMI) was noted in 193 patients (54%). Stroke was noted in 101 patients (28%). Ischemic heart disease (IHD) was noted in 38 patients (11%). AOMI was more common in males (110 patients, 57%) than in females (43%). Seventy-three (73) patients (20.3%) died. Predictors of death were age over 60 and the existence of more than two cardiovascular risk factors. Conclusion: Diabetic macroangiopathy is a major cause of morbidity and mortality. The development and implementation of a prevention and management program is essential.