Durvalumab plus tremelimumab for the treatment of advanced neuroendocrine neoplasms of gastroenteropancreatic and lung origin

Single immune checkpoint blockade in advanced neuroendocrine neoplasms (NENs) shows limited efficacy; dual checkpoint blockade may improve treatment activity. Dune (NCT03095274) is a non-randomized controlled multicohort phase II clinical trial evaluating durvalumab plus tremelimumab activity and safety in advanced NENs. This study included 123 patients presenting between 2017 and 2019 with typical/atypical lung carcinoids (Cohort 1), G1/2 gastrointestinal (Cohort 2), G1/2 pancreatic (Cohort 3) and G3 gastroenteropancreatic (GEP) (Cohort 4) NENs; who progressed to standard therapies. Patients received 1500 mg durvalumab and 75 mg tremelimumab for up to 13 and 4 cycles (every 4 weeks), respectively. The primary objective was the 9-month clinical benefit rate (CBR) for cohorts 1-3 and 9-month overall survival (OS) rate for Cohort 4. Secondary endpoints included objective response rate, duration of response, progression-free survival according to irRECIST, overall survival, and safety. Correlation of PD-L1 expression with efficacy was exploratory. The 9-month CBR was 25.9%/35.5%/25% for Cohorts 1, 2, and 3 respectively. The 9-month OS rate for Cohort 4 was 36.1%, surpassing the futility threshold. Benefit in Cohort 4 was observed regardless of differentiation and Ki67 levels. PD-L1 combined scores did not correlate with treatment activity. Safety profile was consistent with that of prior studies. In conclusion, durvalumab plus tremelimumab is safe in NENs and shows modest survival benefit in G3 GEP-NENs; with one-third of these patients experiencing a prolonged OS.

Strain- and serotype-dependent affinity of Shiga toxin-producing Escherichia coli for bovine milk fat globules

Shiga toxin-producing Escherichia coli (STEC) are widely detected in raw milk products intended for human consumption. Although STEC are a worldwide public health problem, the pathogenicity of STEC in cheese remains unclear. In fact, bacterial association with compounds in raw milk cheeses could reduce their pathogenicity. A previous study showed the association of 2 STEC strains with raw milk cream in a natural creaming assay. Different concentrations of each strain were required to saturate the cream. In this study, we hypothesized that all STEC strains could be associated with milk fat globules (MFG) in raw milk and that the bacterial load required for saturation of the cream is serotype dependent. We evaluated the affinity of STEC strains belonging to the O157:H7, O26:H11, and O103:H2 serotypes for bovine raw milk cream and analyzed saturation of the cream layer by natural creaming assay. We used 12 STEC strains and 3 strains belonging to another pathotype to assess the effects of serotypes on this phenomenon. We performed sucrose density gradient centrifugation assays with 2 STEC model strains to confirm the results obtained by natural creaming. The localization of STEC within MFG-enriched creams was observed by confocal and electron microscopy. We recovered approximately 10 times more STEC from the cream layer after natural creaming than from raw bovine milk. The concentration of STEC required to saturate the cream layer (the saturation concentration) was estimated for each strain by nonlinear regression, highlighting a strain and serotype effect. Moreover, the concentration of STEC in the cream was milk fat level dependent. However, even in nonsaturating conditions, a high level of STEC was still present in the aqueous phase, after fat separation. Thus, natural creaming should not be used as the sole preventive measure to remove STEC from naturally contaminated raw milk. The results of our study suggest that cream saturation is a complex mechanism, most likely involving specific interactions between STEC and raw MFG.

Epidemiology and impact of frailty in patients with atrial fibrillation in Europe

BACKGROUND

Frailty is a medical syndrome characterised by reduced physiological reserve and increased vulnerability to stressors. Data regarding the relationship between frailty and atrial fibrillation (AF) are still inconsistent.

OBJECTIVES

We aim to perform a comprehensive evaluation of frailty in a large European cohort of AF patients.

METHODS

A 40-item frailty index (FI) was built according to the accumulation of deficits model in the AF patients enrolled in the ESC-EHRA EORP-AF General Long-Term Registry. Association of baseline characteristics, clinical management, quality of life, healthcare resources use and risk of outcomes with frailty was examined.

RESULTS

Among 10,177 patients [mean age (standard deviation) 69.0 (11.4) years, 4,103 (40.3%) females], 6,066 (59.6%) were pre-frail and 2,172 (21.3%) were frail, whereas only 1,939 (19.1%) were considered robust. Baseline thromboembolic and bleeding risks were independently associated with increasing FI. Frail patients with AF were less likely to be treated with oral anticoagulants (OACs) (odds ratio 0.70, 95% confidence interval 0.55-0.89), especially with non-vitamin K antagonist OACs and managed with a rhythm control strategy, compared with robust patients. Increasing frailty was associated with a higher risk for all outcomes examined, with a non-linear exponential relationship. The use of OAC was associated with a lower risk of outcomes, except in patients with very/extremely high frailty.

CONCLUSIONS

In this large cohort of AF patients, there was a high burden of frailty, influencing clinical management and risk of adverse outcomes. The clinical benefit of OAC is maintained in patients with high frailty, but not in very high/extremely frail ones.

Effect of the vision suppression on the graphomotor gesture in school aged children typically developed and with handwriting disorders

Introduction

The knowledge aboutthe integration of letter motor programs during learning to write support the idea of an interdependence of visual and kinesthetic controls to direct the strokes.

Objectives

The objective of our study is to analyze the effect of the vision suppression both on the postural-gestural organization and on the spatial/temporal/kinematic parameters in a prescriptural task.

Methods

35 school aged children with handwriting disorders (HD group) aged 6-11 years and 35 matched typical children were included in the study. They performed a prescriptural task of copying a cycloid line of loops, carried out under two conditions, with open eyes versus closed eyes. Postural-gestural measures were recorded with two video cameras allowing 2D reconstruction of the gesture. Spatial/temporal/kinematic measures were recorded with a digital pen.

Results

The HD group showed a significantly poorer postural control and an improvement in the spatial/temporal/kinematic parameters of the loops when they closed their eyes compared to eyes open. In typical group, the postural-gestural organization became significantly more mature but with no significant influence on the spatial/temporal/kinematic parameters of the loops.

Conclusions

HDs could be partly explained by a deficit in the processing of proprioceptive/kinesthetic feedback and a disruptive effect of the visual control on the quality of the prescriptural drawings. The ability to direct the strokes would remain dependent on sensory feedbacks, themselves insufficiently efficient, which would lead to difficulties in reaching a proactive control of handwriting. These results should be able to enhance clinical practices and to contribute to clinical decision making processes for handwriting disorders remediation.

Disclosure

No significant relationships.

Unplanned Pregnancy in women with mental disorder

Introduction

Few studies have investigated the level of planning of pregnancy among women with mental disorder and associated risk factors.

Objectives

The purpose of this study was to determine the associated factors to UP and psychopathological consequences.

Methods

A cross sectional study was conducted at the Perinatal Mental Health Unit of the Hospital Clínic in Barcelona. The total sample comprised 675 consecutive pregnant women with diagnosis of mental disorder (DSM-IV criteria), seen between January 2006 and December 2018. Clinical, psychometric and socio-demographic variables were collected at the first visit. Pregnancy planning was assessed by a question “Was this pregnancy planned?” with three possible answers: 1) Yes, it was planned and has been well received; 2) No, it was not planned but it has been well received; and 3) No, it was an accident. Response 1 was coded as “planned pregnancy” and responses 2 and 3 as “Unplanned Pregnancy”.

Results

38.4% of the sample had an UP. Younger age, lower levels of education, Latin-American population, multiparity, financials problems and poor relationship with the partner were associated with UP in women with mental disorder. The mean EPDS and STAI scores and the presence of self-harming thoughts were significantly higher in women with UP.

Conclusions

UP was associated with more depressive and anxious symptoms and more self-harming thoughts. It is necessary to promote reproductive health care for women with mental disorders and to take into account their reproductive life plan, especially in those with risk factors described.

Disclosure

No significant relationships.

Automated 3D Fetal Brain Segmentation Using an Optimized Deep Learning Approach

BACKGROUND AND PURPOSE

MR imaging provides critical information about fetal brain growth and development. Currently, morphologic analysis primarily relies on manual segmentation, which is time-intensive and has limited repeatability. This work aimed to develop a deep learning-based automatic fetal brain segmentation method that provides improved accuracy and robustness compared with atlas-based methods.

MATERIALS AND METHODS

A total of 106 fetal MR imaging studies were acquired prospectively from fetuses between 23 and 39 weeks of gestation. We trained a deep learning model on the MR imaging scans of 65 healthy fetuses and compared its performance with a 4D atlas-based segmentation method using the Wilcoxon signed-rank test. The trained model was also evaluated on data from 41 fetuses diagnosed with congenital heart disease.

RESULTS

The proposed method showed high consistency with the manual segmentation, with an average Dice score of 0.897. It also demonstrated significantly improved performance (P < .001) based on the Dice score and 95% Hausdorff distance in all brain regions compared with the atlas-based method. The performance of the proposed method was consistent across gestational ages. The segmentations of the brains of fetuses with high-risk congenital heart disease were also highly consistent with the manual segmentation, though the Dice score was 7% lower than that of healthy fetuses.

CONCLUSIONS

The proposed deep learning method provides an efficient and reliable approach for fetal brain segmentation, which outperformed segmentation based on a 4D atlas and has been used in clinical and research settings.

Regional Differences in Gamma-Aminobutyric Acid and Glutamate Concentrations in the Healthy Newborn Brain

BACKGROUND AND PURPOSE

Gamma-aminobutyric acid and glutamate system disruptions may underlie neonatal brain injury. However, in vivo investigations are challenged by the need for special ¹H-MR spectroscopy sequences for the reliable measurement of the neurotransmitters in this population. We used J-edited ¹H-MR spectroscopy (Mescher-Garwood point-resolved spectroscopy) to quantify regional in vivo gamma-aminobutyric acid and glutamate concentrations during the early postnatal period in healthy neonates.

MATERIALS AND METHODS

We prospectively enrolled healthy neonates and acquired Mescher-Garwood point-resolved spectroscopy spectra on a 3T MR imaging scanner from voxels located in the cerebellum, the right basal ganglia, and the right frontal lobe. CSF-corrected metabolite concentrations were compared for regional variations and cross-sectional temporal trends with advancing age.

RESULTS

Fifty-eight neonates with acceptable spectra acquired at postmenstrual age of 39.1 (SD, 1.3) weeks were included for analysis. Gamma-aminobutyric acid (+ macromolecule) (2.56 [SD, 0.1]) i.u., glutamate (3.80 [SD, 0.2]), Cho, and mIns concentrations were highest in the cerebellum, whereas NAA (6.72 [SD, 0.2]), NAA/Cho, Cr/Cho, and Glx/Cho were highest in the basal ganglia. Frontal gamma-aminobutyric acid (1.63 [SD, 0.1]), Glx (4.33 [SD, 0.3]), Cr (3.64 [SD, 0.2]), and Cho concentrations were the lowest among the ROIs. Glx, NAA, and Cr demonstrated a significant adjusted increase with postmenstrual age (β = 0.2-0.35), whereas gamma-aminobutyric acid and Cho did not.

CONCLUSIONS

We report normative regional variations and temporal trends of in vivo gamma-aminobutyric acid and glutamate concentrations reflecting the functional and maturational status of 3 distinct brain regions of the neonate. These measures will serve as important normative values to allow early detection of subtle neurometabolic alterations in high-risk neonates.

Diabetic mitochondria are resistant to palmitoyl CoA inhibition of respiration, which is detrimental during ischemia

The bioactive lipid intermediate palmitoyl CoA (PCoA) can inhibit mitochondrial ADP/ATP transport, though the physiological relevance of this regulation remains unclear. We questioned whether myocardial ischemia provides a pathological setting in which PCoA regulation of ADP/ATP transport would be beneficial, and secondly, whether the chronically elevated lipid content within the diabetic heart could make mitochondria less sensitive to the effects of PCoA. PCoA acutely decreased ADP‐stimulated state 3 respiration and increased the apparent K_m for ADP twofold. The half maximal inhibitory concentration (IC₅₀) of PCoA in control mitochondria was 22 µM. This inhibitory effect of PCoA on respiration was blunted in diabetic mitochondria, with no significant difference in the K_m for ADP in the presence of PCoA, and an increase in the IC₅₀ to 32 µM PCoA. The competitive inhibition by PCoA was localised to the phosphorylation apparatus, particularly the ADP/ATP carrier (AAC). During ischemia, the AAC imports ATP into the mitochondria, where it is hydrolysed by reversal of the ATP synthase, regenerating the membrane potential. Addition of PCoA dose‐dependently prevented this wasteful ATP hydrolysis for membrane repolarisation during ischemia, however, this beneficial effect was blunted in diabetic mitochondria. Finally, using ³¹P‐magnetic resonance spectroscopy we demonstrated that diabetic hearts lose ATP more rapidly during ischemia, with a threefold higher ATP decay rate compared with control hearts. In conclusion, PCoA plays a role in protecting mitochondrial energetics during ischemia, by preventing wasteful ATP hydrolysis. However, this beneficial effect is blunted in diabetes, contributing to the impaired energy metabolism seen during myocardial ischemia in the diabetic heart.

What is the role of neurosurgeons in the current management of intracranial aneurysm in France? An analysis of professional practices

STUDY DESIGN

Retrospective observational survey-based study.

INTRODUCTION

In France, intracranial aneurysm (IA) patients are managed by neurosurgeons and by interventional neuroradiologists. The growth of endovascular treatment led us to reflect on the role of neurosurgeons in the management of patients with IA. The present study aimed to highlight the current organization of IA management in France.

METHOD

A 60-question survey was sent to the neurosurgeons in 34 hospitals managing IA patients. Thirty-three questions dealt with standards of care, follow-up procedures and the involvement of the specific specialist.

RESULTS

Twenty-seven centers (79.4%) responded to the survey. A Vascular Multidisciplinary Discussion Team was organized, including both surgeons and neuroradiologists, in 92% of responding centers. There were department protocols in 66% of centers, a local registry in 33% and clinical trials in IA in 60%. Patients with unruptured IA were first seen by a neurosurgeon or by an interventional neuroradiologist, with different practices. For ruptured IA, the neurosurgeons were contacted first in 93% of cases, and were systematically involved in initial intensive care unit management. The patients were hospitalized in the neurosurgery department in 89% of the centers. The neurosurgeons took care of initial follow-up in 85% of the centers, and of lifetime follow-up in 36%. In most centers, radiological monitoring of IA was based on MRI angiography for patients who were embolized or under surveillance, and on CT angiography after microsurgery.

CONCLUSION

Despite the growth of endovascular treatments, the present survey and the literature highlight a major role of neurosurgeons in treatment, follow-up and care coordination.

Simulations of micro-sphere/shell 2D silica photonic crystals for radiative cooling

Passive daytime radiative cooling has recently become an attractive approach to address the global energy demand associated with modern refrigeration technologies. One technique to increase the radiative cooling performance is to engineer the surface of a polar dielectric material to enhance its emittance at wavelengths in the atmospheric infrared transparency window (8-13 µm) by outcoupling surface-phonon polaritons (SPhPs) into free-space. Here we present a theoretical investigation of new surface morphologies based upon self-assembled silica photonic crystals (PCs) using an in-house built rigorous coupled-wave analysis (RCWA) code. Simulations predict that silica micro-sphere PCs can reach up to 73 K below ambient temperature, when solar absorption and conductive/convective losses can be neglected. Micro-shell structures are studied to explore the direct outcoupling of the SPhP, resulting in near-unity emittance between 8 and 10 µm. Additionally, the effect of material composition is explored by simulating soda-lime glass micro-shells, which, in turn, exhibit a temperature reduction of 61 K below ambient temperature. The RCWA code was compared to FTIR measurements of silica micro-spheres, self-assembled on microscope slides.

Validity of kinematics measures to assess handwriting development and disorders with a graphomotor task

Introduction

Handwriting disorder is considered to be one of the major public health problems among school-aged children worldwide. All the scales in the literature use handwriting tasks but it could be interesting to investigate a more accurate assessment of handwriting difficulties before the development and acquisition of handwriting as such.

Objectives

The objective of our study is to examine the validity of a prescriptural task consisting of copying a line of cycloid loops in the diagnosis of handwriting disorders.

Methods

35 children with handwriting disabilities and 331 typically developing right-handed children in primary school, aged 6-11 years old, were included in the study. They performed a copy of a line of cycloid loops, in an ecological setting, with a paper sheet put on the table. The kinematic measures were recorded with a digital pen. A Receiver Operating Characteristic method (ROC curve) was used to determine whether the loops line copy may be a sensitive test to diagnose handwriting disorders.

Results

Six kinematic variables recorded during the prescriptural task were found to be relevant markers of handwriting disorders with a sensibility between 0.743 and 0.880: strokes number, total and effective drawing time, in-air pauses times, loops number, number of peaks velocity.

Conclusions

The graphomotor task of copying a line of cycloid loops showed a good sensitivity to diagnose handwriting disorders and appeared to be a good predictor test, more particularly with the variables reflecting the strokes temporal organization.Drawing loops is a rapid graphomotor task, useful for exploring prerequisites of handwriting in screening for handwriting disorders.

The anti-ageing effects of a natural peptide discovered by artificial intelligence

OBJECTIVE

As skin ages, impaired extracellular matrix (ECM) protein synthesis and increased action of degradative enzymes manifest as atrophy, wrinkling and laxity. There is mounting evidence for the functional role of exogenous peptides across many areas, including in offsetting the effects of cutaneous ageing. Here, using an artificial intelligence (AI) approach, we identified peptide RTE62G (pep_RTE62G), a naturally occurring, unmodified peptide with ECM stimulatory properties. The AI-predicted anti-ageing properties of pep_RTE62G were then validated through in vitro, ex vivo and proof of concept clinical testing.

METHODS

A deep learning approach was applied to unlock pep_RTE62G from a plant source, Pisum sativum (pea). Cell culture assays of human dermal fibroblasts (HDFs) and keratinocytes (HaCaTs) were subsequently used to evaluate the in vitro effect of pep_RTE62G. Distinct activities such as cell proliferation and ECM protein production properties were determined by ELISA assays. Cell migration was assessed using a wound healing assay, while ECM protein synthesis and gene expression were analysed, respectively, by immunofluorescence microscopy and PCR. Immunohistochemistry of human skin explants was employed to further investigate the induction of ECM proteins by pep_RTE62G ex vivo. Finally, the clinical effect of pep_RTE626 was evaluated in a proof of concept 28-day pilot study.

RESULTS

In vitro testing confirmed that pep_RTE62G is an effective multi-functional anti-ageing ingredient. In HaCaTs, pep_RTE62G treatment significantly increases both cellular proliferation and migration. Similarly, in HDFs, pep_RTE62G consistently induced the neosynthesis of ECM protein elastin and collagen, effects that are upheld in human skin explants. Lastly, in our proof of concept clinical study, application of pep_RTE626 over 28 days demonstrated anti-wrinkle and collagen stimulatory potential.

CONCLUSION

pep_RTE62G represents a natural, unmodified peptide with AI-predicted and experimentally validated anti-ageing properties. Our results affirm the utility of AI in the discovery of novel, functional topical ingredients.

P6422Physician vs machine: an innovative ST-elevation myocardial infarction pathway through artificial intelligence

Background

The diagnosis of ST-Elevation Myocardial Infarction (STEMI) has traditionally relied on a cardiologist's interpretation of an Electrocardiogram (EKG). This cumbersome process is costly, inefficient and out of date. Artificial Intelligence (AI) -guided algorithms can provide point-of-care, accurate STEMI diagnosis that will facilitate STEMI management.

Purpose

To demonstrate the feasibility of an automated AI-guided EKG analysis for STEMI diagnosis.

Methods

An observational, retrospective, case-control study. Sample: 8,511 EKG cardiologist-annotated records, including 4,255 STEMI cases. Records excluded patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes by wavelet system, segmentation of each EKG into individual heartbeats (90,592 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, “STEMI” and “Not-STEMI” classes were considered for each heartbeat, individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

The model achieved an accuracy of 96.5%, with a sensitivity of 96.3%, and a specificity of 96.8%.

Conclusion(s)

1) AI-guided interpretation of the EKG can reliably diagnose STEMI; 2) AI algorithms can be incorporated into ambulance systems for pre-hospital diagnosis, single page activation, emergency department bypass, facilitating more efficient STEMI pathways.

P6421Can cardiologists rely on artificial intelligence to identify the culprit vessel in STEMI?

Background

The importance of culprit lesion identification is critical for risk stratification of a patient with an ST-Elevation Myocardial Infarction (STEMI). The aforementioned provide patients with a more elaborated strategy of management and treatment either they are treated with PCI or less invasive techniques such as thrombolysis. We report a novel approach that employs AI-guided electrocardiogram (EKG) algorithms for rapid and accurate identification of the culprit STEMI vessel.

Purpose

To create an innovative, machine learning tool for a more effective risk stratification of STEMI patients.

Methods

An observational, retrospective, case-control study. Sample: 2,542 exclusively STEMI diagnosis EKG records that included post discharge feedback from healthcare centers, confirming diagnosis and culprit vessel (Left Main Coronary Artery [LMCA]; Left Anterior Descending [LAD]; Right Coronary Artery [RCA]; Left Circumflex Artery [LCX]; Saphenous Vein Graft [SVG]). Records excluded other patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes using a wavelet system, segmentation of each EKG into individual heartbeats (27,125 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented; “LCMA”, “LAD”, “LCX”, “RCA”, “SVG”, and “No Information” classes were considered for each heartbeat; individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample was used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

Global Accuracy: 79.4%; LAD: Sensitivity 86.2%; Specificity 84.8%. RCA: Sensitivity 85.7%; Specificity 83.7%. LCX: Sensitivity 43.5%; Specificity 96.9%.

Conclusions

Coupling an AI-augmented algorithm and 12-lead EKG provides encouraging results for STEMI culprit vessel localization. Overall, risk stratification is possible for individual lesions located in the LAD and RCA. However, our approach yielded uncertain results in the LCX territory. We plan to continue to exploring variables for improvement of our results.

P5241Balancing limited resources, infra-structure deficits & cultural differences in sustaining the growth of LATIN telemedicine program

Background

In resource-constrained nations, population-based AMI coverage is daunting. Telemedicine can transform with efficient, cost-effective and scalable programs. We present our data with screening >780,000 patients with innovative hub and spoke strategies.

Purpose

Scientifically pristine protocols, rigorous training, unflinching quality assurance, technology upgrades and education of broad stakeholders are essential attributes for creating population-based AMI programs.

Methods

Latin America Telemedicine Infarct Network (LATIN) required methodical groundwork during a 12-month pilot prior to its formal launch and sustenance for 5 years. It involved scrupulous site selection, technology, and telemedicine optimization and system-wide process metrics. Spokes are the LATIN nucleus and require constant (3-T) training: Triage, Telemedicine, and Transportation. Plus, a mandatory deconstruct of their role in LATIN, of urgent transfer and desist non-critical care. Telemedicine requires constant upgrading of platform, tele-equipment and cloud computing. Ambulance availability is a constant challenge as is the battle with payers. Data entry has required meticulous training and oversight. Strict QA processes have monitored critical metrics: Spokes (Door In Door Out, DIDO and Transport Times); Hubs (Door to Balloon Times, D2B); Telemedicine Platform (Time to Telemedicine Diagnosis, TTD).

Results

Linear growth is observed in the number of sites and telemedicine screenings with simultaneous and sustained improvements in D2B and TTD. 784,395 patients were screened at 350 LATIN centers (Brazil 143, Colombia 118, Mexico 82, Argentina 7). With expanded reach, 8,440 (1.08%) patients were diagnosed and 3,924 (46.5%) urgently reperfused, including 3,048 (77.7%) with PCI. Time to Telemedicine Diagnosis (TTD) was 3 min, tele-accuracy 98.9%, D2B 51 min and in-hospital morality 5.2%. Major reasons for non-treatment were insurance, lack of ICU beds and delayed presentation.

Conclusions

As other regions of the world develop large, population-based AMI management initiatives, LATIN can provide important lessons in the sustainability of these processes.

P1466Can physicians trust a machine learning algorithm to diagnose ST elevation myocardial infarction?

Background

For the past years, the medical field has been taking advantage of the endless possibilities that Artificial Intelligence (AI) provides. Using computer-aided devices that can perform and interpret electrocardiograms (EKG) accurately pushes current healthcare boundaries. We present the LUMENGT-AI, this model can handle large datasets, multiclass diagnoses, complex EKG morphology, and still detect ST Elevation MI (STEMI) accurately.

Purpose

To develop an innovative AI-based system for automated STEMI specific EKG analysis.

Methods

An observational, retrospective, case-control study. Sample: 8,511 EKG records, previously diagnosed as “normal”, “abnormal” (over 200 conditions) or “STEMI” (4,255 cases). Records excluded patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing: detection of QRS complexes by wavelet system, segmentation of each EKG into individual heartbeats (90,592 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented, “STEMI” and “Not-STEMI” classes were considered for each heartbeat, individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample were used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

Ground Truth Score – Accuracy (94.1%), Sensitivity (87.8%), Specificity (98.1%) – see the comparison to published data in Table.

Conclusions

A statistical analysis allowed us to compare STEMI recognition efficiency between physicians and our model. The LUMENGT algorithm results secured its place as a reliable tool to diagnose STEMI faster and more accurately than physicians.

P6418The continued proficiency of artificial intelligence for interpreting EKG: single lead EKG for STEMI culprit lesion localization

Background

Traditionally, the 12-lead electrocardiogram (EKG) has been used for diagnosing ST-Elevation Myocardial Infarction (STEMI) and for identifying the culprit lesion. We have previously demonstrated the impact of combining a Single Lead approach with Artificial Intelligence (AI) to replace tasks previously dominated by the 12 lead EKG. This research explores the role of the single lead EKG in identifying a culprit lesion.

Purpose

To test the use of a single lead approach to accurately locate the culprit vessel.

Methods

An observational, retrospective, case-control study. Sample: 2,542 exclusively STEMI diagnosis EKG records that included post discharge feedback from healthcare centers, confirming diagnosis and culprit vessel (Left Main Coronary Artery [LMCA]; Left Anterior Descending [LAD]; Right Coronary Artery [RCA]; Left Circumflex Artery [LCX]; Saphenous Vein Graft [SVG]). Records excluded other patient and medical information. The sample was derived from the private International Telemedical Systems (ITMS) database. LUMENGT-AI Algorithm was employed. Preprocessing:detection of QRS complexes using a wavelet system, segmentation of each EKG into individual heartbeats (27,125 total beats) with fixed window of 0.4s to the left and 0.9s to the right of main QRS; Classification: A 1-D convolutional neural network was implemented; “LCMA”, “LAD”, “CX”, “RCA”, “SVG”, and “No Information” classes were considered for each heartbeat per lead; individual probabilities were aggregated to generate the final label for each record. Training & Testing: 90% and 10% of the sample was used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with NVidia GTX 1070 GPU, 8GB RAM.

Results

Accuracy: 77.4% Lead III; Sensitivity: LMCA (Lead aVL 25%); LAD (Lead aVF 87.8%); RCA (Leads V1, V3 92.9%); LCX (Lead aVL 21.7%).

Conclusions

Our results yielded the dominance of a specific single lead to each culprit vessels, aVF for LAD and V1 and V3 for RCA. We continue testing with different algorithms to search for reliable results for the LMCA and LCX. Nonetheless, conjugating a Single Lead EKG with an AI-augmented algorithm enables faster and easier management for patients that present with STEMI affecting the LAD and RCA territories.

B-78 Social Skills Training for Verbal Aggression in Conserved Adults with Traumatic Brain Injury, Schizophrenia, and Schizoaffective Disorder

Objective

This pilot study examined the effectiveness of a social skills training (SST) program aimed to decrease verbal aggressive behavior and increase prosocial skills of conserved adults.

Method

Conserved adults (N = 10) with traumatic brain injury, schizophrenia, and schizoaffective disorder received SST for six weeks, an hour weekly, and they were assessed pre- and post-intervention. The Overt Aggression Scale-Modified for Neurorehabilitation-Extended was used to measure aggressive behaviors. Aggressive behavior to self, objects, and others was rated by facility staff that were not involved in the SST. Acquisition of social skills was rated by facility staff on the number of observed prosocial behavior (self-initiates greeting, responds to greeting, expresses gratitude). Only verbal aggression and prosocial scores were used given SST’s content. A paired samples t-test was conducted to evaluate the pre-post effectiveness and effect sizes.

Results

Aggression improved from M = 2.83 (SD = 3.39) to M = 1.00 (SD = 1.98), an improvement of 1.83, but was not statistically significant (t[8] = 2.28, p = .052; Cohen’s d = .76). 95% confidence interval ranged from -0.02 to 3.67. Prosocial behaviors improved from M = 8.67 (SD = 2.35) to M = 9.83 (SD = 2.41), an improvement of 1.17, but was not statistically significant (t[8] = -1.56, p = .158; Cohen’s d = .52). 95% confidence interval ranged from -2.90 to .56.

Conclusions

Effect sizes showed a decrease in aggression and social skills improvement of the participants. This SST is promising and should be examined with randomized controlled trial studies with larger sample sizes.

[Clinico-electroencephalographic variants in pharmacoresistant mesial temporal lobe epilepsy]

INTRODUCTION

Focal epilepsy secondary to mesial temporal sclerosis (MTS) is one of the main causes of refractory epilepsy. It is typically associated with frontotemporal discharges in the electroencephalogram (EEG), a characteristic image in the magnetic resonance scan and a probability of post-operative remission above 70%.

AIMS

To identify different patterns of ictal propagation in surface EEG recordings in patients with refractory epilepsy and MTS, and to analyse their relation with the post-operative outcome.

PATIENTS AND METHODS

We conducted a retrospective review of the medical records of patients with refractory epilepsy secondary to MTS evaluated in the Epilepsy Surgery Programme of the Hospital de Clinicas, Montevideo (n = 30). The propagation of ictal rhythms was analysed in time windows of three seconds, and propagation maps were produced for each seizure.

RESULTS

Six patterns were identified: ipsilateral temporal (type 1; 37%), bilateral frontotemporal with (type 2A; 22%) or without (type 2B; 17%) extension to suprasylvian regions, alternating temporal (type 3; 13%), unilateral suprasylvian (type 4; 7%) and bilateral at onset (type 5; 3%). The type 1 pattern was associated with classic clinical features and a favourable post-operative outcome. The clinical variants were associated with extratemporal EEG propagation. Patients with reflex seizures continued with post-operative seizures. Overall, no unambiguous relation was found between the ictal EEG pattern and the post-operative outcome.

CONCLUSIONS

The ictal EEG pattern does not allow for a surgical prognosis in patients with epilepsy secondary to MTS. The history of reflex seizures in these patients may be a red flag suggesting a less favourable surgical outcome.

Handwriting disorders in children with developmental coordination disorder (DCD): Exploratory study

Introduction

Although more than 85% of children with DCD are affected by handwriting disorders, their characteristics and underlying mechanisms remain poorly known.

Objectives

We aim to better identify the nature of handwriting disorders in subtyping DCD children.

Methods

School children aged between 5 to 15 years and exhibited a DCD (according to DSM-5) are eligible for inclusion. They were classified in three subtypes of DCD: ideomotor (IM), visual-spatial and/or constructional (VSC), and mixed (MX). They were assessed with a standardized handwriting evaluation including quality and speed and a clinical observation of motor gestual developmental and temporal-spatial organization of handwriting highlighting six qualitative criteria: irregular handwriting (criterion 1), immaturity of handwriting gesture (criterion 2), excessive pressure of the pen on the paper (criterion 3), neuro-vegetative responses (criterion 4), trembling (criterion 5), slow handwriting velocity (criterion 6). Two groups are established: children with poor handwriting (PH) and children with dysgraphia (DysG).

Results

While 89% of children have handwriting disorders, only 20% exhibit dysgraphia. IM DCD is characterized by an immaturity of handwriting gesture and is associated with PH. Dysgraphia appears only in VSC and MX DCD which are characterized by the association of criteria 1, 2, 3, and 4. This association appears to more than 80% in DysG. Slow handwriting velocity is constant between PH and DysG.

Conclusion

Immaturity of handwriting gesture is a possible underlying mechanism of poor handwriting. Dysgraphia is associated with specific impairments in spatial organization of letters and in motor control of handwriting gesture.

Disclosure of interest

The authors have not supplied their declaration of competing interest.

Knowing about you: eliciting dimensions of personhood within tuberculosis care

BACKGROUND

Knowing someone with tuberculosis (TB) as a person, rather than defining them by their illness, is part of recognising their dignity and unique individuality, and a requirement for effective care.

OBJECTIVE

An adaptation of the Patient Dignity Question (PDQ) was formalised for persons receiving treatment for active TB or latent tuberculous infection (LTBI), and its impact was evaluated for both the person and health care providers (HCPs).

DESIGN

Individuals with active TB or LTBI receiving treatment in Winnipeg, MB, Canada, were asked the PDQ as part of routine care. Patients and HCPs were subsequently invited to evaluate the application of the PDQ.

RESULTS

Of the 58 participants who responded to the PDQ, 97% felt both that it was important to ask about them as an individual, and that the PDQ should be asked of all patients, while 55% thought it made a difference to their care. Thirty-eight per cent of HCPs said they learned something new about their patient, and 31% said it influenced their sense of connectedness with and sense of empathy for patients, as well as their personal satisfaction in providing care.

CONCLUSION

Formalising a dignity question as part of person-centred care provides a mechanism to create a respectful environment that is caring of the most marginalised who carry the burden of TB.

Five Years of Multidisciplinary Care in Hereditary Cancer: Our Experience in a Spanish University Hospital

OBJECTIVE

To analyse the evolution of a multidisciplinary heredofamilial cancer unit (HFCU) in a university hospital.

METHODS

This was a retrospective analysis of the activity of our HFCU in its first 5 years of existence.

RESULTS

Between July 2010 and July 2015, 1,518 patients from 1,318 families attended our HFCU. Genetic testing was offered to 862 patients. Of those, 833 (96.6%) accepted testing, with available results for 636 (76.4%). Pathogenic mutations in BRCA1 and BRCA2 were found in 175 patients. Lynch syndrome and adenomatous polyposis were the most frequent syndromes diagnosed (151/175, 86.3%) among 17 different syndromes studied. Of the 404 patients without a previous genetic diagnosis in the family, 62 (15.3%) were found to have mutations in disease-causing genes. Prophylactic surgery and follow-up (33.7%) or follow-up only (66.3%) was proposed for mutation carriers according to international guidelines and patients' preferences.

CONCLUSION

We have a high mutation detection rate, genetic test acceptance, and compliance with risk reduction strategies. However, there is room for improvement, especially in genetic testing timing, considering that an increase in the indications for genetic testing is expected.