Identification Of Cases Research Articles

The potential for species distribution models to distinguish source populations from sinks.

While species distribution models (SDM) are frequently used to predict species occurrences to help inform conservation management, there is limited evidence evaluating whether habitat suitability can reliably predict intrinsic growth rates or distinguish source populations from sinks. Filling this knowledge gap is critical for conservation science, as applications of SDMs for management purposes ultimately depend on these typically unobserved population or metapopulation dynamics. Using linear regression, we associated previously published population level estimates of intrinsic growth and abundance derived from a Bayesian analysis of mark-recapture data for 17 bird species found in the contiguous United States with SDM habitat suitability estimates fitted here to opportunistic data for these same species. We then used the area under the ROC curve (AUC) to measure how well SDMs can distinguish populations categorized as sources and sinks. We built SDMs using two different approaches, boosted regression trees (BRT) and generalized linear models (GLM), and compared their source/sink predictive performance. Each SDM was built with presence points obtained from eBird (a web-available database) and 10 environmental variables previously selected to model intrinsic growth rates and abundance for these species. We show that SDMs built with opportunistic data are poor predictors of species demography in general; both BRT and GLM explained very little spatial variation of intrinsic growth rate and population abundance (median R2 across 17 species was close to 0.1 for both SDM methods). SDMs, however, estimated higher suitability for source populations as compared to sinks. Out of 13 species which had both source and sink populations, both BRT and GLM had AUC values greater than 0.7 for 7 species when discriminating between sources and sinks. Habitat suitability have the potential to be a useful measure to indicate a population's ability to sustain itself as a source population; however more research on a diverse set of taxa is essential to fully explore this potential. This interpretation of habitat suitability can be particularly useful for conservation practice, and identification of explicit cases of when and how SDMs fail to match population demography can be informative for advancing ecological theory.

Implementation of a Standardized Tool for Root Cause Analysis Selection.

This study sought to determine if a standardized root cause analysis (RCA2) selection algorithm, developed by the Veterans Affairs, would select high-risk events for RCA. Physician-entered incident reports for all surgical service admissions and perioperative visits were queried over 12 months in the DATIX Clinical Incident Management System. Independent reviewers assigned potential harm and event frequency scores using an institutional scoring system and then calculated and rounded average scores. These were classified using RCA2 terminology (catastrophic, major, moderate, minor for harm; frequent, occasional, uncommon, remote for frequency). The scores were then evaluated with the standardized Safety Assessment Code Matrix (SAC) algorithm from the National Patient Safety Foundation's RCA2 guidelines to determine Potential Harm Scores. The SAC combines severity and probability to determine the necessity of conducting an RCA. Catastrophic and major high-frequency events (matrix score = 3) were classified as "RCA recommended." The study then compared cases selected for RCAs using the updated RCA2 algorithm against cases selected using a current, institutional-specific RCA selection process. One hundred four cases were reviewed, comprising 20 catastrophic, 48 major harm, 26 moderate harm, and 10 minor harm events. After removing 9 high-variance cases, our institution's current selection process selected 18 cases for RCAs, including 6/20 catastrophic, 8/39 major harm, and 4/36 moderate/minor harm events. Only 17.3% of cases had an RCA completed, while the standardized RCA2 algorithm recommended investigation for 56.7% of patient safety events, based on SAC Matrix scoring. Current RCA selection processes rendered 4 RCAs on low potential harm or low-frequency events, while 45 potential high-frequency, high potential harm events did not complete RCAs. Standardizing the selection of patient safety incidents for RCA using the RCA2 algorithm improves case identification based on the event frequency and potential harm score. Thus, this algorithm has the potential to advance patient safety.

Towards malaria elimination: a case–control study to assess associated factors to malaria relapses in the extra-Amazon Region of Brazil from 2008 to 2019

BackgroundMalaria is an infectious disease caused by the Plasmodium species and is a global burden. When not treated correctly, it can reemerge as a relapse or recrudescence. Malaria relapse cases can contribute to maintaining active transmission chains and can influence the patient to develop severe malaria, potentially leading to hospitalization or death. The objective of this study is to estimate the number of malaria relapse cases in the extra-Amazon region of Brazil and to investigate the associated factors.MethodsThis is a case–control study that analyses malaria infections caused by Plasmodium vivax, as reported in Notifiable Diseases Information System (Sinan) for the Brazilian extra-Amazon region (an area not endemic for the disease) from 2008 to 2019. For the identification of relapse cases, deduplication record linkage processes in R software were used. Malaria relapses were defined as the case group, and new malaria infections were defined as the control group. Logistic regression models were used to assess associated factors.ResultsOf the 711 malaria relapses, 589 (82.8%) were first relapses. Most relapses (71.6%) occurred between 30 and 120 days after the previous infection. Malaria relapses are spread throughout the extra-Amazon region, with a higher concentration near big cities. Driver occupation was found to be a common risk factor compared to other occupations, along with asymptomatic individuals. Other associated factors were: being infected in the Brazilian Amazon region, having follow-ups for malaria relapses, and having parasite density of the previous infection higher than 10,000 parasites per mm3.ConclusionsThis study provides evidence that allows malaria health surveillance services to direct their efforts to monitor cases of malaria in the highest risk segments identified in this study, particularly in the period between 30 and 120 days after being infected and treated. Relapses were associated to driver occupation, absence of symptoms, infection in endemic areas of Brazil, being detected through active surveillance or routine follow-up actions, and with parasitaemia greater than 10,000 parasites per mm3 in the previous infection. Improving cases follow-up is essential for preventing relapses.

Dwarfism-related skeletal dysplasia in Italy. Multi-analytic study of 8th century CE human remains from Azzio (Varese) and biocultural implications of a pathology

Skeletal dysplasias are a broad family of genetic disorders, often challenging to diagnose even in clinical literature without molecular analysis. Some cases of possible skeletal dysplasia have also been identified in osteoarchaeological samples, although achieving a definitive diagnosis is fraught with difficulties. This paper presents the analysis of the osteological remains of AZ-III-3, discovered in the archaeological context of the Church of Sant’Antonio and Eusebio in Azzio (Varese province, Italy). The study aims to demonstrate that even with limited skeletal elements, a diagnosis can be hypothesised using macroscopic morphometric and radio diagnostic techniques. These methods, compared with clinical and paleopathological literature, have allowed for the identification of a rare Italian case of dwarfism-related skeletal dysplasia. This contribution seeks to address the biocultural presence of individuals affected by these skeletal dysplasias, listing and discussing all published Italian cases, including that of AZ-III-3, whose chronological framework was established through both archaeological context analysis and 14C dating.

Identification of Uncertainty Cases in Robots with Focus on Additive Manufacturing Technology: A Mini Review

Despite more than three decades since the beginning of Additive Manufacturing (AM), many challenges and issues prevent the industrialization of this technology. In fact, productivity is related to repetitive production of the same part under the same fabrication conditions. Currently, it is difficult to guarantee this repetitive production due to uncertainty issues, which represents the main obstacle of AM industrialization. In this paper, the uncertainty issues can be divided into two levels. The first level is related to the used AM machine itself which can be considered as robot of 3 degrees of freedom (x, y and z). In addition to its movement in three directions, this robot (AM machine) extrudes melted materials. The second level is related to the associated robots with 3D printing machines. In addition to summarizing some previous works and reviews, this mini review has the objective to provide new ideas to develop new strategies to overcome some uncertainty issues to contribute to the industrialization of AM technology. Furthermore, it paves the way to establish a concurrent AM / robotics loop in order to use AM for robotics and robotics for AM. The different developments should lead to elaborating Industrialization Standard for AM (IS4AM) where the different findings and recommendations can be classified in logical ways to deal with different AM techniques and materials.

Validation of electronic health record data to identify hospital-associated Clostridioides difficile infections for retrospective research.

Clostridioides difficile infection (CDI) research relies upon accurate identification of cases when using electronic health record (EHR) data. We developed and validated a multi-component algorithm to identify hospital-associated CDI using EHR data and determined that the tandem of CDI-specific treatment and laboratory testing has 97% accuracy in identifying HA-CDI cases.

Patient motivation: A concept analysis.

Patient motivation is crucial in maintaining health-improving activities and helping patients recover from illnesses. Despite extensive research on patient motivation, this concept has not been clearly defined and remains ambiguous. The latest analysis of patient motivation was over two decades ago, thus necessitating the need to reexamine it in more updated literature. This study aims to explore the concept of patient motivation. The eight-step approach of Walker and Avant was used: concept selection, determining analysis aim, identifying concept use, defining attributes, model case identification, borderline and contrary case identification, antecedents and consequences identification, and empirical referent identification. Five databases, CINAHL, Cochrane, Medline, PubMed, ProQuest, and ScienceDirect, were searched for published works between 2014 and 2024 using the keywords "patient" and "motivation." The identified attributes of patient motivation are a psychological drive, a desire to adopt healthy behaviors, and goal-directed action. Antecedents of patient motivation are self-efficacy, provider-patient communication, and social support. Patient motivation leads to consequences, including healthier lifestyles and greater adherence and compliance. The present concept analysis draws upon current literature to suggest the antecedents, attributes, and consequences of patient motivation. Nurses can promote healthier lifestyles and greater adherence and compliance among patients by employing techniques to raise self-efficacy and provide social support while enhancing patient-centered interactions.

Case Identification of Depression in Inpatient Electronic Medical Records: Scoping Review.

Electronic medical records (EMRs) contain large amounts of detailed clinical information. Using medical record review to identify conditions within large quantities of EMRs can be time-consuming and inefficient. EMR-based phenotyping using machine learning and natural language processing algorithms is a continually developing area of study that holds potential for numerous mental health disorders. This review evaluates the current state of EMR-based case identification for depression and provides guidance on using current algorithms and constructing new ones. A scoping review of EMR-based algorithms for phenotyping depression was completed. This research encompassed studies published from January 2000 to May 2023. The search involved 3 databases: Embase, MEDLINE, and APA PsycInfo. This was carried out using selected keywords that fell into 3 categories: terms connected with EMRs, terms connected to case identification, and terms pertaining to depression. This study adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines. A total of 20 papers were assessed and summarized in the review. Most of these studies were undertaken in the United States, accounting for 75% (15/20). The United Kingdom and Spain followed this, accounting for 15% (3/20) and 10% (2/20) of the studies, respectively. Both data-driven and clinical rule-based methodologies were identified. The development of EMR-based phenotypes and algorithms indicates the data accessibility permitted by each health system, which led to varying performance levels among different algorithms. Better use of structured and unstructured EMR components through techniques such as machine learning and natural language processing has the potential to improve depression phenotyping. However, more validation must be carried out to have confidence in depression case identification algorithms in general.

Imported malaria cases by Plasmodium falciparum and Plasmodium vivax in Mexican territory: Potential impact of the migration crisis

BackgroundAs the migratory flow to the USA has intensified in recent months, health problems associated have been identified. The aim of this work was the identification of malaria cases imported into Mexican territory. MethodsOperational definitions of suspected and confirmed cases were used for investigation of malaria cases. Detection of parasitic entities by thick blood smear and molecular biology served as a confirmatory test. With the characteristics of the cases, a heat map was made to determine common clinical pictures. Finally, epidemiological analysis of cases was performed for the construction of timelines of imported malaria and the tracing of migratory routes. ResultsTwelve migrants from four countries were treated for presenting clinical symptoms with suspected dengue or malaria. Malaria was confirmed and two Plasmodium species were identified. From the epidemiological dates of arrival in Mexico, onset of symptoms and migratory routes, we speculate that ten cases acquired P. vivax during their crossing through Honduras, El Salvador or Guatemala. For the Guinea cases, we conclude that there was African importation of P. falciparum. ConclusionThe epidemiological panorama of malaria cases imported into Mexico show the need to join efforts to ensure universal access to health services, with the objective of timely detection of imported cases.

Cases of endophthalmitis caused by Candida albicans and Candida dubliniensis identified via internal transcribed spacer deep sequencing

BackgroundWe report two cases of fungal endophthalmitis induced by Candida species identified based on internal transcribed spacer 1 (ITS1) sequencing.Case presentationIn two cases, endophthalmitis was suspected, and the patients underwent pars plana vitrectomy. Case 1 was a 64-year-old woman with a history of cataract surgery 10 days prior. She had a history of anal primary melanoma, which metastasized throughout the body and subsequently relapsed. Vitreous culture and ITS-1 deep sequencing revealed the presence of the rare fungus, Candida dubliniensis. Case 2 was a 54-year-old man with a history of liver cancer and kidney failure. Culture methods and ITS1 deep sequencing both revealed the presence of Candida albicans. Both patients exhibited good visual prognoses after treatment with topical and systemic antibiotics.ConclusionsWe present two cases of fungal endophthalmitis caused by two Candida species identified by both the culture method and ITS1 deep sequencing. The fungal pathogen was identified by ITS deep sequencing three days after sample submission; the culture method yielded results after 1 week. These findings support the applicability of ITS1 sequencing for timely pathogen identification for cases of fungal endophthalmitis and provide detailed taxonomic information at the species level.

Situación de los asentamientos informales en el AMSS y sus virtudes frente a la ciudad consolidada

This article seeks to expose the current situation of the Precarious Urban Settlements (PUS) in the Metropolitan Area of San Salvador (AMSS), their typological relationships, distribution in the territory and social aspects that have been identified both in the metropolitan research and through research within a representative sample. Among the findings its shown that population densities are greater than the metropolitan average, high concentrations of PUS in densely populated municipalities yields data of approximately 20% of the metropolitan population living in settlements which in turn occupy only 7% of the metropolitan territory; high typological dispersion in which it is evident that in 63.5 % of these settlements only 15.6 % of precarious housing is contained. This characterization allowed the identification of most representative study cases to carry out a qualitative study, which for this case brought together four settlements in the municipality of Ciudad Delgado whose study revealed aspects of livelihoods and habitability that allow comparisons with the consolidated city. ILIA: Investigaciones Latinoamericanas en Ingeniería y Arquitectura, No. 01, 2024: 62-66.

Effectiveness of Antileishmanial Treatments in Three Endemic Areas of Colombia: A Community-Based Cohort Study.

The effectiveness of treatment of cutaneous leishmaniasis (CL) in rural settings remains underexplored. This study assessed the effectiveness of standard antileishmanial treatments using a community-based approach supported by mobile health (mHealth) in three rural areas of Colombia. From January 2018 to September 2021, we assessed treatment outcomes, adherence, and adverse drug reactions in CL patients, with the support of the Guaral+ST app. Treatment decisions were made by providers at health facilities at each site in accordance with national guidelines, whereas treatment follow-up and presumptive case identification were made by trained community leaders and health agents at the community level. In total, 231 participants received antileishmanial treatment (63 received miltefosine, 110 meglumine antimoniate, and 58 pentamidine). Disease presentation was mild (median number of lesions = 1, interquartile range [IQR]: 1-2) and of short duration (1.5 months, IQR: 1-3). The strategy yielded information on the therapeutic outcomes in 81% of study participants. Effectiveness, measured as the proportion of cure at 90 to 180 days, was 86.3% (95% CI: 73.3-93.48) for miltefosine; 77.6% (67.5-85.3) for meglumine antimoniate, and 73.1% (59.0-83.6) for pentamidine. The effectiveness of pentamidine in children ≤10 years old was 79.4% (61.6-90.3). This is one of the few reports of effectiveness of pentamidine in children with prospective data collection in the Americas. Adverse drug reactions occurred in 32% of patients, most frequently with meglumine antimoniate. Our findings demonstrate that standard antileishmanial treatments are effective in rural areas where the disease is endemic and that mHealth has a pivotal role in improving patient follow-up and data collection on therapeutic outcomes.

A hybrid framework with large language models for rare disease phenotyping.

Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports. We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. SemEHR, a dictionary-based NLP tool, is employed to extract rare disease mentions from clinical notes. To refine the results and improve accuracy, we leverage various LLMs, including LLaMA3, Phi3-mini, and domain-specific models like OpenBioLLM and BioMistral. Different prompting strategies, such as zero-shot, few-shot, and knowledge-augmented generation, are explored to optimize the LLMs' performance. The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. LLaMA3 and Phi3-mini achieve the highest F1 scores in rare disease identification. Few-shot prompting with 1-3 examples yields the best results, while knowledge-augmented generation shows limited improvement. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients. The hybrid approach combining dictionary-based NLP tools with LLMs shows great promise for improving rare disease identification from unstructured clinical reports. By leveraging the strengths of both techniques, the method demonstrates superior performance and the potential to uncover hidden rare disease cases. Further research is needed to address limitations related to ontology mapping and overlapping case identification, and to integrate the approach into clinical practice for early diagnosis and improved patient outcomes.

Community-Based Mycetoma Surveillance in Uganda: Identifying Knowledge Gaps and Training of Community Health Workers to Improve Case Detection.

Mycetoma is an uncommon and neglected tropical disease in Uganda. We aimed to assess baseline knowledge and provide community health workers (CHWs) in Northern Uganda with knowledge to identify and refer presumptive mycetoma cases. Between March and August 2023, we conducted a concurrent triangulation mixed methods study among CHWs in Gulu and Pader districts on mycetoma. We conducted a 1 day in person training on mycetoma. Quantitative data were collected before (pretest), immediately (immediate posttest) and six months (6-month posttest) after the training and results compared using paired sample t test or one-way ANOVA. Qualitative data were collected using four focused group discussions, audio recorded, and analyzed using thematic content analysis. Forty-five CHWs were enrolled, mostly male (66.7%, n = 30), with a median age of 36 years (IQR 29 43). Out of a total score of 18, the baseline mean knowledge score was 7±2.42, improving to 11±1.99 immediately posttest (p<0.001), and 10±2.35 at 6 months (p<0.001), without additional training. Significant knowledge improvements at 6 months were observed among female participants (p = 0.004), those aged 30 40 years (p = 0.031) or 40+ years (p = 0.035), and those with secondary education (p = 0.007). Over 6 months, CHWs screened 2,773 adults, identifying and referring 30 presumptive mycetoma cases. Qualitative findings revealed challenges and barriers to early identification and referral of mycetoma presumptive cases including limited knowledge, stigma, myths, lack of an indigenous name for mycetoma, delayed decision making, and transportation barriers. This study highlights a significant knowledge gap among CHWs about mycetoma, with substantial improvement following training. The identification of presumptive cases by CHWs reflects their potential in community-based surveillance, emphasizing the need to integrate well-trained CHW to lead efforts for mycetoma surveillance and capacity building to enhance health outcomes in Uganda.

COVID-19 Modeling: A Review

The SARS-CoV-2 viruses and their triggered COVID-19 pandemic have fundamentally reshaped the world in almost every aspect, their evolution and influences remain. While over a million of literature have been produced on these unprecedented, overwhelming global disaster, one critical question is open: How has COVID-19 been quantified globally? This further inspires many other questions: What COVID-19 problems have been modeled? How have modeling methods in areas such as epidemiology, artificial intelligence (AI), data science, machine learning, deep learning, mathematics and social science played their roles in characterizing COVID-19? Where are the gaps and issues of these COVID-19 modeling studies? What are the lessons for quantifying future disasters? Answering these questions involves the analysis of a very broad spectrum of literature across different disciplines and domains. Distinguishing from specific efforts, this review takes the first attempt to generate a systematic, structured and contrastive landscape and taxonomy of global COVID-19 modeling. First, the surveyed problems span over a full range of COVID-19, including epidemic transmission processes, case identification and tracing, infection diagnosis and medical treatments, non-pharmaceutical interventions and their influence, drug and vaccine development, psychological, economic and social influence and impact, and misinformation, and so on. Second, the reviewed modeling methods traverse all relevant disciplines, from statistic modeling to epidemic modeling, medical analysis, biomedical analysis, AI, deep and machine learning, analytics, and simulation. Critical analyses further identify significant issues and gaps, for example, simple techniques and similar problems have been overwhelmingly addressed everywhere, while intrinsic and foundational issues and deep insights have been overlooked. The review discloses significant opportunities for more deeply, effectively and uniquely quantifying COVID-19-like global disasters from their intrinsic working mechanisms, interactions and dynamics.

7564 Adrenal Pheochromocytoma In A Clinically Inapparent Adrenal Mass

Abstract Disclosure: L. Medina Mora: None. S. Htoo: None. A. Sanchez Ruiz: None. M. Harshan: None. A. Busta: None. Introduction: Pheochromocytomas (PCC) are rare tumors that arise from the adrenal medulla, with an estimated annual incidence of 0.8 per 100,000 person-years. These tumors have been associated with significant morbidity and mortality and are considered among the most life-threatening endocrine diseases, particularly if left undiagnosed. Its symptoms can be related to the tumor's mass effect or catecholamine excess. As a result, they can mimic other conditions, often leading to delayed or incorrect diagnosis. A study conducted on 296 patients with PCC treated from 2005 to 2016 found that 61% were discovered incidentally through cross-sectional imaging (CSI). The widespread use of CSI in recent years has led to the identification of asymptomatic cases that would have otherwise gone undetected. In this case, we present a middle-aged female who was incidentally found to have a PCC. Case Report: A 59-year-old female with a history of hypertension, cerebrovascular accident, pulmonary hypertension, systolic heart failure, mitral valve replacement, and asthma presented to the clinic for evaluation of a right adrenal lesion measuring 4.2 x 3.5 cm found during an emergency room visit during the evaluation of chest pain. She had no known family history of brain or endocrine disorders. Her lab results showed elevated plasma metanephrine and normetanephrine to 578.4 (reference range: 0-88) and 459.9 (reference: 0-244), respectively. Additionally, her 24-hour urine metanephrine was elevated to 984 mcg (normal range: 36-209), and Chromogranin A was 164.3 (reference range: 0-101). The rest of her labs, including cortisol, renin, aldosterone, and DHEA-S were unremarkable. A CT with and without contrast revealed a 3.0 x 3.5 x 5.1 cm solid non-calcified right adrenal mass measuring 39 Hounsfield units (HU). In addition, it measured 53 HU in the venous phase and 61 HU in the 15-minute delayed phase (relative washout of &amp;lt;1%; absolute washout of &amp;lt;7%). The patient was treated with alpha-blockers and underwent a robotic-assisted right adrenalectomy. The pathology was significant for a 5.4 cm well-differentiated PCC. The tumor had extended into but not beyond the adrenal capsule. The postoperative course of the patient was uncomplicated. Discussion: After a PCC is detected, the most effective treatment option is to surgically remove it. This procedure necessitates a combination of alpha and beta-blockade to regulate blood pressure and prevent a hypertensive crisis. Despite the success of surgery, there is still uncertainty about the optimal follow-up after the procedure, which often leads to many patients being lost during the process. Furthermore, even a decade after the initial surgery, there remains a substantial likelihood of illness reoccurrence or metastasis, making the situation even more complex. Therefore, it is crucial to adhere to a lifelong follow-up plan that includes annual biochemical testing. Presentation: 6/2/2024

Deregulated Expression of Long Non-coding RNA ZFAS1 as a Predictive Biomarker for Respiratory Failure in Severe Pneumonia Children and Its Impact on Clinical Outcome

Abstract Objective Severe pneumonia is a common pediatric disease, often complicated by respiratory failure (RF). The expression changes of long non-coding RNA zinc finger antisense 1 (ZFAS1) were examined in children with severe pneumonia, as well as their predictive value in the occurrence of RF and poor outcomes. Methods A total of 120 children with severe pneumonia were included, 60 of whom had RF. RT-qPCR was used to detect mRNA levels. Deaths during the follow-up period were recorded through a 28-day follow-up survey. Receiver operating characteristic (ROC) curve and Kaplan Meier (K-M) plot were drawn to display diagnostic and predictive values, with the help of multiple logistic and Cox regression analysis. Results A sharp rise of serum ZFAS1 was tested in severe pneumonia children, providing a area under the receiver operator characteristic curve (AUC-ROC) of 0.920, with a sensitivity of 81.67% and a specificity of 90.00%. Serum ZFAS1 (OR = 5.832, 95% CI = 2.283–14.899) was found to be associated with the occurrence of RF after adjusting other clinical indexes, with an AUC-ROC of 0.843. ZFAS1 (HR = 4.624, 95% CI = 1.318–16.217, P &lt; 0.05) was an independent influence factor for the poor prognosis. Cases with high ZFAS1 levels had worse clinical outcomes. Conclusion Monitoring serum ZFAS1 levels is helpful in assessing severe pneumonia in children, especially for early identification of cases with RF. High serum ZFAS1 levels have a certain predictive value for poor prognosis in patients.

Comparing AI/ML approaches and classical regression for predictive modeling using large population health databases: Applications to COVID-19 case prediction

BackgroundResearch comparing artificial intelligence and machine learning (AI/ML) methods with classical statistical methods applied to large population health databases is limited. ObjectivesThis retrospective cohort study aimed to compare the predictive performance of AI/ML algorithms against conventional multivariate logistic regression models using linked health administrative data. MethodsUsing Ontario's population health databases, we created a cohort of residents of the city of Ottawa, Ontario, who underwent a PCR test for COVID-19 between March 10, 2020, and May 13, 2021. Using demographic, socio-economic and health data (including COVID-19 PCR test results and available, symptom data), we developed predictive models for the purpose of COVID-19 case identification using the following approaches: classical multivariate logistic regression (LR); deep neural network (DNN); random forest (RF); and gradient boosting trees (GBT). Model performance comparisons were made using the area under the curve (AUC) swarm plot for 10-fold cross-validation. ResultsThe cohort consisted of n = 351,248 Ottawa residents tested for COVID-19 during the study period. Among whom, a total of n = 883,879 unique COVID-19 tests were performed (2.6 % positive test results). Inclusion of COVID-19 symptoms data in the analysis improved model performance and variable predictive value across all tested models (p < 0.0001), with the 10-fold cross-validation AUC increasing to near or over 0.7 in all models when symptoms data were included. In various pairwise comparisons, the GBT method had the highest predictive ability (AUC = 0.796 ± 0.017), significantly outperforming multivariate logistic regression and the other AI/ML approaches. ConclusionsConventional multivariate regression-based models are better than some and worse than other machine learning algorithms to provide good predictive accuracy in a moderate dataset with a reasonable number of features. However, whenever possible, the AI/ML GBT approach should be considered.

Effect of case identification changes on pre-hospital intubation performance indicators in an Australian helicopter emergency medical service.

A 45-min interval from injury to intubation has been proposed as a performance indicator for severe trauma patient management. In the Sydney pre-hospital system a previous change in case identification systems was associated with activation delay. We aimed to determine if this also decreased the proportion of patients intubated within this benchmark. Retrospective cohort study of patients intubated by a helicopter emergency medical service (HEMS) over two time periods. Period 1 dispatch was via HEMS crew directly screening the computerised dispatch system, and period 2 was via paramedics in a central control room. Times from emergency call to intubation were compared. In the HEMS crew screening period 46/58 (79.31%) intubations met the target, compared with 137/314 (43.6%) in the central control period (P < 0.001). The median (interquartile range) time to intubation in the direct crew screening period was 33 (25-41) min, versus the central control period at 47 (38-60) min (P < 0.001). On multivariate modelling, distance to the scene was related to time to intubation (P < 0.001; Incident Rate Ratio = 1.018, 95% confidence interval 1.015-1.020) as was dispatch system, entrapment/access difficulty and indication for intubation (all P < 0.001). Time from emergency call to intubation was significantly shorter in the HEMS screening period where all non-trapped cases less than 50 km distant were intubated within the 45-min benchmark. There was no distance where intubation within 45 min could be assured for non-trapped patients in the central control period due to dispatch delays.

B-108 Delta Check Performance Assessment by Using Real-WorldData at the Temple University Health System​

Abstract Background Delta check is a post-analytic tool focusing on pre-analytical, analytical and post-analytical errors. It can be sensitive in detecting isolated errors affecting a single patient, as opposed to moving patient averages, which is another QC tool for detecting errors that affect a cohort/population of patients. As a computer-based system on selected tests, delta checks are to detect excessive changes from prior value in the patient test result and to detect possible specimen errors such as misidentified or compromised samples before results are reported. It may also play a role in detecting examination(analytical) issues and clinically significant results. If delta checks exceed established limits, the result is flagged. There is a common agreement that measurands with low indices of individuality (&amp;lt;0.6) make good candidates for the identification of cases of sample misidentification than higher indices of individuality (&amp;gt;1.4). CLSI EP33 Use of Delta Checks in the Medical Laboratory guidelines recommends that laboratories assess the validity of current delta check parameters by reviewing retrospective data on flagged results to determine if errors are being identified efficiently. At Temple University Health System, delta check limits were established historically by using published data, however, its performance characteristics have not been verified previously. Verification of clinical performance of predefined delta check limits can be performed either through mathematical calculations or via clinical audits. Clinical audits are achieved by documenting the follow-up actions and outcomes of the samples flagged by a delta check rule(s). It has been suggested that this should be performed using a protocolized follow-up procedure to ensure uniformity in the investigation and management. Corey M. et al. shared an excel template, a mathematical model that can be adopted easily by replacing the example data with retrospectively extracted data and modifying the parameters to suit their laboratory’s requirements. Methods We collected up to 30,000 data points for each 12 measurand in the clinical chemistry lab retrospectively. By using the excel template, clinical sensitivity and clinical specificity has been calculated. Furthermore, we created ROC curves and evaluated them using the (YI) Youden Index and AUC (Area Under the Curve). Results In general, YI values were found to be very low, less than 0.6. Highest YI was used to establish new delta check limits for each analyte; only the current creatinine delta check limit was found as effective, and no change required. 11 out of 12 measurand were required a revision of delta check limits and were proposed to replace with lower delta checks. AUC values were found between 0.56-0.794. Na showed the highest AUC, which correlates its low individuality index (0.5) and its effects on effectiveness of the delta check system. Conclusions It is of vital importance to establish a solid follow-up evaluation for delta check alerts and distinguish between integrity issues and clinically significant changes. Conclusively, this endeavor can develop into extensive information for the application, evaluation, and follow-up of delta checks whilst improving diagnostic accuracy and quality assurance.