Clinical Decision Algorithms Research Articles

Machine learning-derived clinical decision algorithm for the diagnosis of hyperfunctioning parathyroid glands in patients with primary hyperparathyroidism.

To train and validate machine learning-derived clinical decision algorithm (MLCDA) for the diagnosis of hyperfunctioning parathyroid glands using preoperative variables to facilitate surgical planning. This retrospective study included 458 consecutive primary hyperparathyroidism (PHPT) patients who underwent combined 4D-CT and sestamibi SPECT/CT (MIBI) with subsequent parathyroidectomy from February 2013 to September 2016. The study cohort was divided into training (first 400 patients) and validation sets (remaining 58 patients). Sixteen clinical, laboratory, and imaging variables were evaluated. A random forest algorithm selected the best predictor variables and generated a clinical decision algorithm with the highest performance (MLCDA). The MLCDA was trained to predict the probability of a hyperfunctioning vs normal gland for each of the four parathyroid glands in a patient. The reference standard was a four-quadrant location on operative reports and pathology. The accuracy of MLCDA was prospectively validated. Of 16 variables, the algorithm selected 3 variables for optimal prediction: combined 4D-CT and MIBI using (1) sensitive reading, (2) specific reading, and (3) cross-product of serum calcium and parathyroid hormone levels and outputted an MLCDA using five probability categories for hyperfunctioning glands. The MLCDA demonstrated excellent accuracy for correct classification in the training (4D-CT + MIBI: 0.91 [95% CI: 0.89-0.92]) and validation sets (4D-CT + MIBI: 0.90 [95% CI: 0.86-0.94]. Machine learning generated a clinical decision algorithm that accurately diagnosed hyperfunctioning parathyroid glands through classification into probability categories, which can be implemented for improved preoperative planning and convey diagnostic certainty. Question Can an MLCDA use preoperative variables for the diagnosis of hyperfunctioning parathyroid glands to facilitate surgical planning? Findings The developed MLCDA demonstrated excellent accuracy for correct classification in the training (0.91 [95% CI: 0.89-0.92]) and validation sets (0.90 [95% CI: 0.86-0.94]). Clinical relevance Using standard preoperative variables, an MLCDA for diagnosing hyperfunctioning parathyroid glands can be implemented to improve preoperative parathyroid localization and included in radiology reports forsurgical planning.

Assessing the need for coronary angiography in high-risk acute coronary syndrome patients using artificial intelligence and computed tomography

Abstract Background/Introduction The use of coronary computed tomography angiography (CCTA) in managing high-risk acute coronary syndrome (ACS) patients is increasingly common. Yet, its role remains unvalidated in this context, posing challenges to traditional clinical decision-making algorithms. Physicians, accustomed to a hierarchical and structured approach involving symptom assessment, electrocardiograms, and biomarkers for deciding on the necessity of invasive coronary angiography (ICA), now face dilemmas when CCTA results challenge established diagnostic pathways and contradict clinical decisions based on usual criteria. Meanwhile, the potential of artificial intelligence (AI) which processes information in a way fundamentally different from human clinical reasoning, has been shown to aid decision-making in cardiovascular medicine. Yet, it has not been tested in this acute setting. Purpose This study aimed to evaluate the efficacy of the Chat Generative Pre-trained Transformer (ChatGPT) in guiding the need for ICA in high-risk ACS patients based on both standard clinical data and CCTA findings. Methods This investigation is a sub-study of a larger research project where high-risk ACS patients (all having a theoretical guideline-based indication for ICA) underwent CCTA prior to ICA. ChatGPT analyzed clinical vignettes containing patient data, electrocardiograms, troponin levels, and CCTA results to determine the necessity of ICA. The AI's recommendations were then compared to actual ICA findings to assess its decision-making accuracy. Results Among 86 patients with a clear indication for ICA, ChatGPT recommended against it for 19 patients, 16 of whom indeed had no significant findings at ICA (Figure). For 67 patients, ChatGPT advised proceeding with ICA, and a significant lesion was confirmed in 58 of them. Consequently, ChatGPT's overall accuracy stood at 86%, with a sensitivity of 95% and a specificity of 64%. The model's negative predictive value was 84%, and its positive predictive value was 87%. Conclusion These preliminary data suggest that ChatGPT can effectively assist in guiding the need for ICA among high-risk ACS patients, potentially reducing unnecessary procedures but further clinical studies to refine AI's role in clinical decision-making are required.ChatGPT's decision as per ICA's results

Development and Implementation of Clinical Decision Algorithms for Oncology.

Decision-making in healthcare often relies on narrative guidelines; however, these instruments are poorly accessible for supporting clinical decision-making. This study explores the application of rule-based decision logic in algorithmic modeling, emphasizing its great potential in clinical decision support and research. Integrating rule-based algorithms with existing information systems and real-world data poses a serious challenge. Integrating decision algorithms with information standards increases their effectiveness across various applications. This study outlines a method for constructing clinical decision trees (CDTs), highlighting their transparency and interpretability, using information standards as a design principle. We use the digitization of the Dutch breast cancer guideline through CDTs as a case study to exemplify their versatility and practical significance. The process step 'primary treatment' has been successfully translated from the narrative guidelines format to the anticipated ted computational format.

Corneal Collagen Cross-linking for Keratoconus in Pediatric and Developmentally Delayed Patients.

Corneal cross-linking (CXL) is the standard of care in patients with keratoconus but presents unique challenges in children and developmentally delayed patients. We present our clinical decision-making algorithm, CXL surgical technique, and outcomes in these groups. A retrospective chart review was undertaken at a tertiary referral center of all patients who underwent CXL for keratoconus at University of Pittsburgh Medical Center (UPMC) Children's Hospital of Pittsburgh between October 1, 2017, and April 1, 2021. Demographic information along with preoperative, intraoperative, and postoperative ophthalmic examination findings were collected. The main outcome measures were indications of CXL, postoperative complications, and visual acuity (VA). Forty-eight eyes of 34 patients [21 patients (30 eyes) with developmental delay (DD) and 13 patients (18 eyes) with no DD (NDD)] underwent epithelium-off, standard CXL. General anesthesia was used for CXL in all patients except for 3 with NDD. A temporary central tarsorrhaphy was performed in all patients with DD and 7 patients with NDD. The remaining got a bandage contact lens. There were no immediate postoperative complications. A trend toward improvement in VA was noted postoperatively. The mean logMAR VA (with habitual correction) was 0.67 preoperatively and 0.57 postoperatively (P = 0.3) in DD and 0.52 and 0.36, respectively (P = 0.13), in NDD. This retrospective review presents a technique for assessment and treatment of keratoconus in children and those with DD. Our technique ensures timely diagnosis and provides a safe method for CXL in these groups. Temporary central tarsorrhaphy is a well-tolerated option to reduce postoperative pain.

End-users’ satisfaction and adoption regarding the implementation of a technology solution for screening and counselling individuals with suspicious COVID-19: a cross-section study

PurposeWe evaluated the end-users’ satisfaction and the adoption of a technology solution embedding a clinical decision algorithm for screening and counselling individuals with suspicious COVID-19.MethodsThis was a cross-sectional study. Data was collected by the startup company Hi! Healthcare Intelligence. Satisfaction was measured using two questions presenting answer options as Likert scales of eleven points (from 0 to 10), in which 0 indicated low satisfaction and 10 indicated high satisfaction. We measured ‘general satisfaction’ through the average of questions 1 and 2. Descriptive analyses were used to summarize the data.ResultsThe average satisfaction regarding the experience in using the technology solution and regarding the ‘recommendation for a friend or family’ was 7.94 (95% confidence interval [CI] 7.60 to 8.28) and 8.14 (95% CI 7.80 to 8.48), respectively. ‘General satisfaction’ was 8.04 (95% CI 7.70 to 8.37). The adoption regarding the implementation of the technology solution was 24.5% (n = 265).ConclusionThe technology solution embedding a clinical decision algorithm for screening and counselling individuals with suspicious COVID-19 presented high satisfaction. One in four (¼) individuals interested in using the technology solution actually adopted it by following the clinical decision algorithm until the end, when counselling was provided.

Optimal Treatment Order With Fibula-Free Flap Reconstruction, Oncologic Treatment, and Dental Implants: A Systematic Review and Meta-Analysis.

Head and neck cancer (HNC) patients benefit from craniofacial reconstruction, but no clear guidance exists for rehabilitation timing. This meta-analysis aims to clarify the impact of oncologic treatment order on implant survival. An algorithm to guide placement sequence is also proposed in this paper. PubMed, Embase, and Web of Science were searched for studies on HNC patients with ablative and fibula-free flap (FFF) reconstruction surgeries and radiotherapy (RTX). Primary outcomes included treatment sequence, implant survival rates, and RTX dose. Of 661 studies, 20 studies (617 implants, 199 patients) were included. Pooled survival rates for implants receiving >60Gy RTX were significantly lower than implants receiving < 60Gy (82.8% versus 90.1%, P =0.035). Placement >1 year after RTX completion improved implant survival rates (96.8% versus 82.5%, P =0.001). Implants receiving pre-placement RTX had increased survival with RTX postablation versus before (91.2% versus 74.8%, P <0.001). One hundred seventy-seven implants were placed only in FFF with higher survival than implants placed in FFF or native bone (90.4% versus 83.5%, P =0.035). Radiotherapy is detrimental to implant survival rates when administered too soon, in high doses, and before tumor resection. A novel evidence-based clinical decision-making algorithm was presented for utilization when determining the optimal treatment order for HNC patients. The overall survival of dental prostheses is acceptable, reaffirming their role as a key component in rehabilitating HNC patients. Considerations must be made regarding RTX dosage, timing, and implant location to optimize survival rates and patient outcomes for improved functionality, aesthetics, and comfort.

Mutation analysis of BCR-ABL1 kinase domain in chronic myeloid leukemia patients with tyrosine kinase inhibitors resistance: a Malaysian cohort study

ObjectiveMutational analysis of BCR::ABL1 kinase domain (KD) is a crucial component of clinical decision algorithms for chronic myeloid leukemia (CML) patients with failure or warning responses to tyrosine kinase inhibitor (TKI) therapy. This study aimed to detect BCR::ABL1 KD mutations in CML patients with treatment resistance and assess the concordance between NGS (next generation sequencing) and Sanger sequencing (SS) in detecting these mutations.ResultsIn total, 12 different BCR::ABL1 KD mutations were identified by SS in 22.6% (19/84) of patients who were resistant to TKI treatment. Interestingly, NGS analysis of the same patient group revealed an additional four different BCR::ABL1 KD mutations in 27.4% (23/84) of patients. These mutations are M244V, A344V, E355A, and E459K with variant read frequency below 15%. No mutation was detected in 18 patients with optimal response to TKI therapy. Resistance to TKIs is associated with the acquisition of additional mutations in BCR::ABL1 KD after treatment with TKIs. Additionally, the use of NGS is advised for accurately determining the mutation status of BCR::ABL1 KD, particularly in cases where the allele frequency is low, and for identifying mutations across multiple exons simultaneously. Therefore, the utilization of NGS as a diagnostic platform for this test is very promising to guide therapeutic decision-making.

Race Adjustment of Pulmonary Function Tests in the Diagnosis and Management of COPD: A Scoping Review.

Increasing evidence suggests that the inclusion of self-identified race in clinical decision algorithms may perpetuate longstanding inequities. Until recently, most pulmonary function tests utilized separate reference equations that are race/ethnicity based. We assess the magnitude and scope of the available literature on the negative impact of race-based pulmonary function prediction equations on relevant outcomes in African Americans with COPD. We performed a scoping review utilizing an English language search on PubMed/Medline, Embase, Scopus, and Web of Science in September 2022 and updated it in December 2023. We searched for publications regarding the effect of race-specific vs race-neutral, race-free, or race-reversed lung function testing algorithms on the diagnosis of COPD and COPD-related physiologic and functional measures. Joanna Briggs Institute (JBI) guidelines were utilized for this scoping review. Eligibility criteria: The search was restricted to adults with COPD. We excluded publications on other lung disorders, non-English language publications, or studies that did not include African Americans. The search identified publications. Ultimately, six peer-reviewed publications and four conference abstracts were selected for this review. Removal of race from lung function prediction equations often had opposite effects in African Americans and Whites, specifically regarding the severity of lung function impairment. Symptoms and objective findings were better aligned when race-specific reference values were not used. Race-neutral prediction algorithms uniformly resulted in reclassifying severity in the African Americans studied. The limited literature does not support the use of race-based lung function prediction equations. However, this assertion does not provide guidance for every specific clinical situation. For African Americans with COPD, the use of race-based prediction equations appears to fall short in enhancing diagnostic accuracy, classifying severity of impairment, or predicting subsequent clinical events. We do not have information comparing race-neutral vs race-based algorithms on prediction of progression of COPD. We conclude that the elimination of race-based reference values potentially reduces underestimation of disease severity in African Americans with COPD.

Serum S100B Level in the Management of Pediatric Minor Head Trauma

Minor head trauma (HT) is one of the most common causes of hospitalization in children. A diagnostic test could prevent unnecessary hospitalizations and cranial computed tomographic (CCT) scans. To evaluate the effectiveness of serum S100B values in reducing exposure to CCT scans and in-hospital observation in children with minor HT. This multicenter, unblinded, prospective, interventional randomized clinical trial used a stepped-wedge cluster design to compare S100B biomonitoring and control groups at 11 centers in France. Participants included children and adolescents 16 years or younger (hereinafter referred to as children) admitted to the emergency department with minor HT. The enrollment period was November 1, 2016, to October 31, 2021, with a follow-up period of 1 month for each patient. Data were analyzed from March 7 to May 29, 2023, based on the modified intention-to-treat and per protocol populations. Children in the control group had CCT scans or were hospitalized according to current recommendations. In the S100B biomonitoring group, blood sampling took place within 3 hours after minor HT, and management depended on serum S100B protein levels. If the S100B level was within the reference range according to age, the children were discharged from the emergency department. Otherwise, children were treated as in the control group. Proportion of CCT scans performed (absence or presence of CCT scan for each patient) in the 48 hours following minor HT. A total of 2078 children were included: 926 in the control group and 1152 in the S100B biomonitoring group (1235 [59.4%] boys; median age, 3.2 [IQR, 1.0-8.5] years). Cranial CT scans were performed in 299 children (32.3%) in the control group and 112 (9.7%) in the S100B biomonitoring group. This difference of 23% (95% CI, 19%-26%) was not statistically significant (P = .44) due to an intraclass correlation coefficient of 0.32. A statistically significant 50% reduction in hospitalizations (95% CI, 47%-53%) was observed in the S100B biomonitoring group (479 [41.6%] vs 849 [91.7%]; P < .001). In this randomized clinical trial of effectiveness of the serum S100B level in the management of pediatric minor HT, S100B biomonitoring yielded a reduction in the number of CCT scans and in-hospital observation when measured in accordance with the conditions defined by a clinical decision algorithm. ClinicalTrials.gov Identifier: NCT02819778.

A247 THE IMPACT OF BIOLOGICS ON MATERNAL AND NEONATAL OUTCOMES IN PREGNANT PATIENTS WITH INFLAMMATORY BOWEL DISEASE AND THEIR ASSOCIATION WITH THERAPEUTIC DRUG LEVELS

Abstract Background Biologic therapies are at the backbone of managing moderate to severe IBD and maintaining clinical remission. The data on the effects of biologic therapy on maternal and neonatal outcomes continues to be limited. To our knowledge, there have been no previous studies specifically investigating whether biologic therapeutic drug levels in pregnant patients are related to maternal and neonatal outcomes. Aims The objective of this study is to determine whether biologic use in pregnancy is associated with adverse maternal and fetal outcomes, and if those outcomes correlate to specific therapeutic drug levels. Methods In this study, we retrospectively evaluate patients at a high-volume pregnancy and inflammatory bowel disease centre at Mount Sinai Hospital in Toronto between January 1st, 2017 to December 31st, 2022. Primary outcomes include maternal complications, such as induction of labour, cesarean section, peripartum infections, placental abruption, preterm labour and pre-eclampsia. Secondary outcomes include neonatal complications, such as preterm birth, low birth weight (ampersand:003C2500g), congenital anomalies and the presence of neonatal infection. These outcomes will be compared to therapeutic drug levels measured in preconception, during pregnancy and post-partum. Results A total of 312 patients were included in our study, of which 152 were on biologic treatment for IBD. Of the biologics population, the majority of patients are on Remicade, followed by Humira and Stelara (Table 1). Preliminary data analysis reveals that there was no significant difference in the rate of miscarriages (10% vs. 6%, P= 0.1), cesarean section (44% vs. 38%, P=0.3) and preterm deliveries (12% vs. 14%, P=0.7) between the biologics vs. non-biologics patient groups. Next round of analysis will include secondary outcomes and therapeutic drug levels. Conclusions Through this study, we hope to add to the literature on the possible safety of maintaining biologic therapy during pregnancy in those with inflammatory bowel disease. The data on proactive therapeutic drug monitoring in pregnant patients may bring to light the importance of its inclusion in clinical decision-making algorithms. Breakdown of therapies in the biologic patient group Funding Agencies None

Abstract 18534: Catheter-Directed Mechanical Thrombectomy: A PERTinent Paradigm Shift

Introduction: The emergence of catheter-directed mechanical thrombectomy (MT) heralded a paradigm shift in the management of pulmonary embolism (PE). There is a paucity of data on the degree to which the availability of this modality has impacted clinical-decision making by the multidisciplinary Pulmonary Embolism Response Team (PERT). We examine data from a single center experience at a large tertiary hospital to shed light. Research Question: How does the recent emergence of MT as a therapeutic strategy impact the approach of a PERT team? Aim: To examine the degree to which the integration of MT into the clinical decision-making algorithm for PE management has impacted the treatment course recommended by a PERT team. Methods: A retrospective analysis was performed to compare PERT recommendations in a contemporary cohort (10/2020-3/2023) to a historical cohort (1/2015-6/2016) prior to the availability of newer generation mechanical thrombectomy catheters in the same institution. Results: The contemporary cohort consisted of 306 patients, of which 50% were treated with advanced therapies including MT, catheter-directed lysis, systemic tPA, or ECMO. In the historical cohort, 28% of patients received advanced therapies. Of those treated with advanced therapies, 84% were MT and 1% were catheter-directed lysis in the contemporary cohort compared to 6% MT and 31% catheter-directed lysis in the historical PERT cohort. Conclusion: The integration of MT into the PERT decision-making process portends a new era in the management of PE. At our center, it significantly expanded the ambit of advanced therapies, such that a majority of patients now receive some form of advanced therapy, rather than anticoagulation alone. This is in stark contrast with the pre-MT era. These findings underscore the importance of a PERT team’s ability to adapt to evolving treatment modalities and highlights the need for continued multidisciplinary expertise in optimizing care for PE patients.

Explantation Site Management: A Decision Algorithm for Re-Implantation.

Dental implants are currently the preferred choice to restore function and esthetics. Nonetheless, explantation is sometimes inevitable in cases with advanced bone loss, implant fracture, or improper implant position. This study aimed to propose an algorithm for re-implantation at the sites of previous failure. There is limited evidence on replacement of failed dental implants, most of which are case reports or clinical trials with small number of patients. To the best of our knowledge, this is the first study proposing a clinical decision algorithm to help clinicians manage implant failures with new fixtures. There are a variety of reasons contributing to implant failure. The etiological factor of failure and the morphology of the residual defect have paramount importance on implant removal techniques and subsequent treatment modalities. There is no consensus on a distinct protocol to replace failed implants. However, the clinicians and patients should know that placing a new implant in an area with a history of failure, regardless of early or late implant failure, may have a lower survival rate.

Literature review and guide for optimal position in implant-based breast reconstruction.

Identification of ideal candidates for prepectoral versus retropectoral implant-based breast reconstruction relies on careful preoperative risk assessment and intraoperative flap evaluation. Few guidelines exist to guide the surgeon's decision-making process when evaluating the preferred plane for implant placement. A literature review was performed to develop clinical decision-making algorithms for direct-to-implant (DTI) reconstruction with acellular dermal matrix (ADM) for patients undergoing prophylactic or therapeutic nipple-sparing mastectomy (NSM) based on patient characteristics, surgical techniques, and outcomes. Prepectoral reconstruction is most suitable for patients with small breasts or macromastia with desire for breast reduction, low-grade ptosis, smaller implant sizes, those undergoing PMRT, and for those who aim to mitigate animation deformity and capsular contracture. Retropectoral reconstruction may be recommended for patients with larger breasts with no desire for size change requiring additional prosthesis support, and in patients who aim to reduce likelihood of rippling and need for subsequent fat grafting procedures to address contour abnormalities. Careful preoperative and intraoperative assessment of reconstruction options for patients undergoing implant-based breast reconstruction is necessary to mitigate complications and produce superior aesthetic outcomes. Decision algorithms may be used to determine ideal surgical techniques based on patient factors, like radiation history and planning, breast size and ptosis, and patient preferences.

One biomarker does not fit all: tailoring anti-infective therapy through utilization of procalcitonin and other specific biomarkers

ABSTRACT Introduction Considering the ongoing increase in antibiotic resistance, the importance of judicious use of antibiotics through reduction of exposure is crucial. Adding procalcitonin (PCT) and other biomarkers to pathogen-specific tests may help to further improve antibiotic therapy algorithms and advance antibiotic stewardship programs to achieve these goals. Areas covered In recent years, several trials have investigated the inclusion of biomarkers such as PCT into clinical decision-making algorithms. For adult patients, findings demonstrated improvements in the individualization of antibiotic treatment, particularly for patients with respiratory tract infections and sepsis. While most trials were performed in hospitals with central laboratories, point-of-care testing might further advance the field by providing a cost-effective and rapid diagnostic tool in upcoming years. Furthermore, novel biomarkers including CD-64, presepsin, Pancreatic stone and sTREM-1, have all shown promising results for increased accuracy of sepsis diagnosis. Availability of these markers however is currently still limited and there is insufficient evidence for their routine use in clinical care. Expert opinion In addition to new host-response markers, combining such biomarkers with pathogen-directed diagnostics present a promising strategy to increase algorithm accuracy in differentiating between bacterial and viral infections. Recent advances in microbiologic testing using PCR or nucleic amplification tests may further improve the diagnostic yield and promote more targeted pathogen-specific antibiotic therapy.

948-P: Glycemic Monitoring Using the Dexcom G6 in Cardiac Surgery

Hyperglycemia is associated with adverse post-surgical outcomes. We evaluated Dexcom G6 accuracy following cardiac surgery. A clinical glucose dataset included 1428 readings of 29 patients, Dexcom data included 45,645 measures. Clinical and Dexcom measures were restricted at least 1 hour after prior measure. Matching clinical and Dexcom measures were required within 5 min. Data were included at least 2 hr after Dexcom insertion and ICU admit. A dataset only measuring ≥24 hrs post ICU admit was created to explore device stability. Patients remained on Dexcom until discharge or 10 days postop. The population was 71% male 14% with known diabetes, 66% who went on intravenous insulin infusion. Figure 1a is Clarke error grid plot of all measures post-ICU admission: 53.5% were Zone A, 45.9% Zone B, and 0.6% (n=5) Zones D or E. Figure 1b uses restricted dataset beginning 24 hours post-ICU admission: 55.9% in Zone A, 43.9% in Zone B, and 0.2% in Zone D. MARD between clinical and Dexcom measures was 20.6% and 21.6% in post-ICU admission dataset and dataset excluding first 24 hours after ICU admission. Almost 100% of Dexcom G6 and clinical data matching points fell within areas considered as giving clinically correct decisions (Zone A) and clinically uncritical decisions (Zone B). If CGM readings are used for clinical decision-making, glucose targets or insulin dosing algorithms may need adjustment. As technology evolves, this device may limit glycemic fluctuations. Disclosure S.R.Insler: None. B.J.Wakefield: None. J.F.Bena: None. A.Debs: None. K.Brake: None. I.Nwosu: None. M.Lansang: Research Support; Dexcom, Inc., Abbott, Alertgy Inc.

Decision-making Algorithm for the Surgical Treatment of Degenerative Lumbar Spondylolisthesis of L4/L5.

A retrospective analysis of prospectively collected data. To report the decision-making process for decompression alone (DA) and decompression and fusion (DF) at a tertiary orthopedic center and compare the operative outcomes between both groups. Controversy exists around the optimal operative treatment for DLS, either with DF or DA. Although previous studies tried to establish specific indications, clinical decision-making algorithms are needed. Patients undergoing spinal surgery for DLS at L4/5 were retrospectively analyzed. A survey of spine surgeons was performed to identify factors influencing surgical decision-making, and their association with the surgical procedure was tested in the clinical data set. We then developed a clinical score based on the statistical analysis and survey results. The predictive capability of the score was tested in the clinical data set with a receiver operating characteristic (ROC) analysis. To evaluate the clinical outcome, two years follow-up postoperative Oswestry Disability Index (ODI), postoperative low back pain (LBP) (Numeric Analog Scale), and patient satisfaction were compared between the DF and DA groups. A total of 124 patients were included in the analysis; 66 received DF (53.2%) and 58 DA (46.8%). Both groups showed no significant differences in postoperative ODI, LBP, or satisfaction. The degree of spondylolisthesis, facet joint diastasis and effusion, sagittal disbalance, and severity of LBP were identified as the most important factors for deciding on DA or DF. The area under the curve of the decision-making score was 0.84. At a cutoff of three points indicating DF, the accuracy was 80.6%. The two-year follow-up data showed that both groups showed similar improvement in ODI after both procedures, validating the respective decision. The developed score shows excellent predictive capabilities for the decision processes of different spine surgeons at a single tertiary center and highlights relevant clinical and radiographic parameters. Further studies are needed to assess the external applicability of these findings.

Automatic body part identification in real-world clinical dermatological images using machine learning.

Dermatological conditions are prevalent across all population sub-groups. The affected body part is of importance to their diagnosis, therapy, and research. The automatic identification of body parts in dermatological clinical pictures could therefore improve clinical care by providing additional information for clinical decision-making algorithms, discovering hard-to-treat areas, and research by identifying new patterns of disease. In this study, we used 6,219 labelled dermatological images from our clinical database, which were used to train and validate a convolutional neural network. As a use case, qualitative heatmaps for the body part distribution in common dermatological conditions was generated using this system. The algorithm reached a mean balanced accuracy of 89% (range 74.8%-96.5%). Non-melanoma skin cancer photos were mostly of the face and torso, while hotspots of eczema and psoriasis image distribution included the torso, legs, and hands. The accuracy of this system is comparable to the best to-date published algorithms for image classification challenges, suggesting this algorithm could boost diagnosis, therapy, and research of dermatological conditions.

Stress and anxiety

The menopausal transition is often accompanied by psycho-vegetative symptoms, including stress and anxiety symptoms. Identifying stress and anxiety and intervening early can have an enormous public health impact. Health care practitioners like obstetrician-gynecologists or family doctors play a critical role in the diagnosis, prevention and treatment of stress and anxiety (disorders), as they often represent women’s primary medical contact during the menopausal transition. However, they frequently don’t feel confident in identifying and treating mental health problems. The aim of the presentation is to summarize current knowledge from RCT’s, systematic reviews, and meta-analyses on diagnostics and treatment options, and to provide clinical decision-making algorithms. The recent literature suggests pharmacological, (cognitive) behavioral, and complementary treatments. The decision about which one to use for a specific patient should be discussed together with the patient.

Creating a clinical decision-making algorithm in order to build a one health knowledge repository to help support and improve the public health surveillance system

Creating a clinical decision-making algorithm in order to build a one health knowledge repository to help support and improve the public health surveillance system

Clinical Correlation of Left Ventricular Geometric Patterns at King Abdulaziz Hospital Al-Ahsa Eastern Province

Objective: Exploring the prevalence of alteration in left ventricular (LV) geometry by echocardiography and their correlation with cardiovascular (CV) risk factors and cardiovascular diseases (CVD). Background: Alterations in LV geometry, by echocardiography, is an important prognostic determinant of CVD morbidity and mortality. Yet it is an underutilized tool and has yet to be established in laboratories. Methods: Left ventricular mass index (LVMI) and relative wall thickness (RWT) were calculated by M-mode echocardiography. Patients were classified into four groups based on RWT and LVMI: normal geometry, concentric remodeling (CR), eccentric left ventricular hypertrophy (eLVH), and concentric left ventricular hypertrophy (cLVH). Results: LV geometry patterns revealed normal geometry prevalence (43.46%), followed by CR (30.76%). The commonest CV risk factor was hypertension (HTN) (85%), followed by diabetes mellitus (DM) (72%). A strong association was identified between CVD and LV geometry changes (p-value &lt; 0.005). CVD prevalence among total patients was 66.5% within this group; coronary artery disease (CAD) prevalence was 55.5% (p-value &lt; 0.029), and heart failure (HF) prevalence was 29.6% (p-value &lt; 0.001). Conclusion: We strongly reinforce routine echocardiograms in determining LVM, RWT, and LV geometry patterns. It is an important, underutilized diagnostic and prognostic tool in risk stratification of patients with CVD and altered LV geometry and mass. Future studies for incorporating LVM and RWT in clinical decision algorithms are warranted.