Long-term outcome of retroperitoneoscopic partial versus total adrenalectomy in patients with Cushing's syndrome

BACKGROUND

We analyze the long-term outcome of surgery for Cushing's syndrome (CS) and the influence of the extent of surgical resection on the duration of postoperative cortisone substitution.

METHODS

One-hundred forty-one patients (129 female, 12 males; mean age: 45.7 ± 12.8 years) operated between January 2000 to June 2020 were included in the analysis. Patients suffered from manifest (124) or subclinical (17) CS due to benign unilateral adrenal neoplasia. All tumors were removed by the posterior retroperitoneoscopic approach. 105 patients had total (TA) and 36 partial (PA) adrenalectomies. All patients were discharged with ongoing corticosteroid supplementation therapy.

RESULTS

Follow-up data could be obtained for 83 patients. Twenty-four (1 male, 23 females; mean age 42.3 years) underwent PA and 59 TA (6 males, 53 females; mean age 44.6 years). Mean follow-up time was 107 ± 68 months (range: 6-243 months). The median duration of postoperative corticosteroid therapy was 9.5 months after PA and 11 months after TA (p = 0.1). Significantly, more patients after total adrenalectomy required corticosteroid therapy for more than 24 months (25% vs. 4%; p = 0.03). Recurrent ipsilateral disease occurred in one case after partial adrenalectomy and was treated by completion adrenalectomy. A case of contralateral recurrence associated with subclinical Cushing's syndrome was observed after total adrenalectomy.

CONCLUSIONS

The risk of local recurrence after partial adrenalectomy in CS is low. Cortical-sparing surgery may shorten corticosteroid supplementation therapy after surgery.

POS0464 DIFFERENTIAL MOLECULAR PROFILES IN THE SYNOVIAL TISSUE AND SYNOVIAL FLUID OF PATIENTS WITH RHEUMATOID ARTHRITIS AND PSORIATIC ARTHRITIS

Background

The differential diagnosis of Rheumatoid Arthritis (RA) and Psoriatic arthritis (PsA) is often difficult due to the similarity of symptoms and the unavailability of reliable clinical biomarkers. Molecular alterations have been suggested to contribute to the pathophysiological processes in the knee joint, and it is known that chronic inflammation induces significant changes in the synovial tissue (ST) and synovial fluid (SF) lipidome and proteome.

Objectives

We aimed to evaluate whether specific characteristics in the molecular profiles from ST and SF could support the differential diagnosis of these diseases.

Methods

ST frozen samples of patients affected by RA (n=6), PsA (n=12) and control donors (n=10) were compared using Matrix-Assisted Laser Desorption Ionization Mass Spectrometry Imaging (MALDI-MSI) for spatially resolved lipid analysis. To this end, tissue sections were measured on a RapifleX MALDI-TOF/TOF instrument. Next, a targeted approach based on multiple reaction monitoring (MRM-MS) was performed to further validate the lipidomic alterations reported by MALDI-MSI between RA and PsA tissues. In this case, lipids extracted from SF (control donors (n=4), RA (n=21) and PsA (n=27)) were analyzed in a QTRAP 4000 mass spectrometer for the targeted analysis of 84 lipid species. Finally, a quantitative proteomic analysis was carried out on FFPE ST from RA (n=13), PsA (n=13) and controls (n=8) by nLC-MS/MS analysis using a TimsTOF Pro system (Bruker). Statistical analyses were performed using GraphPad Prism, Metaboanalyst and Perseus software.

Results

Lipid profiles in ST from PsA and RA were unequivocally distinguished by MALDI-MSI followed by PCA-DA, and were also different comparing with control tissues. Interestingly, several lipid species, including sphingomyelins, phosphatidylcholines (PC) and phosphatidylethanolamines (PE), presented the greatest separation power to classify RA and PsA tissue samples. ANOVA analysis found 35 lipid species significantly different among the study groups, most of them significantly increased in RA and PsA compared to controls. Particularly, 11 lipids showed higher levels in PsA tissues compared with RA, including several PC and PE. The spatial distribution of these PE species was associated with areas of the sublining layer with increased vascularity and inflammatory cell infiltrates, according to MALDI-MSI images. On the other hand, RA and PsA patients were also correctly classified based on the SF levels of all quantified lipid species according to PCA and clustering analysis. Finally, the proteomic analysis quantified around 2,500 distinct proteins in the ST, including several related with lipid metabolism. Near 300 proteins showed altered abundance in the pathological tissues compared to healthy controls (FDR 0.01%, Figure 1A), being the small subset increased in controls mainly extracellular matrix proteins. The comparison between RA and PsA ST led to the identification of a panel of 36 proteins discriminating the two tissues with high statistical significance (p-value <0.01). In this comparison, all proteins except two appeared increased in RA (Figure 1B). A discriminant analysis shows the usefulness of this protein panel to differentiate the two diseases (Figure 1C).

Figure 1.

Results from the proteomic analysis carried out on synovial tissues. A) Heatmap showing the differential protein profiles between synovial tissues (PsA and RA) and healthy controls (CTL), at FDR 0.01. B) Characteristic protein panel discriminating PsA and RA tissues (p-value < 0.01). C) Discriminant analysis performed using this protein panel.

Conclusion

Our study shows distinct molecular profiles between RA and PsA synovial tissue and synovial fluid, and reports potential clinically useful lipid and protein markers for the differential diagnosis of these diseases.

Disclosure of Interests

None declared.

Transcatheter aortic valve replacement in severe aortic stenosis and cardiac amyloidosis: a systematic review and meta-analysis

Background

Aortic stenosis (AS) and cardiac amyloidosis (CA) are typical degenerative diseases of the elderly. According to recent studies, up to 16% of patients referred to transcatheter aortic valve replacement (TAVR) have a concomitant diagnosis of CA. Until recently, TAVR in patients with CA and AS has been considered futile, following the results of small observational studies. However, few studies recently suggested a beneficial impact of TAVR in patients with AS and CA as compared with medical therapy alone.

Purpose

To clarify the efficacy and safety profile of TAVR in CA-AS patients.

Methods

We performed a systematic review and meta-analysis of studies evaluating the risk of mortality after TAVR in CA-AS patients as compared with medical therapy. Moreover, we performed a systematic review and descriptive meta-analysis of studies reporting outcomes and complication rates of TAVR in CA-AS patients as compared with patients with AS alone.

Results

We identified 4 observational studies reporting data on mortality in CA-AS patients treated with either TAVR or medical therapy. Mortality was significantly lower in patients undergoing TAVR (OR 0.23, 95% CI 0.07–0.73, I2=0%, NNT=2.6) as compared with medical therapy. A sensitivity analysis with hazard ratio as effect estimate showed consistent results. Then, we identified 4 observational studies reporting data on mortality, re-hospitalizations and periprocedural complications of TAVR in CA-AS patients as compared with patients with AS alone. We found higher rates of mortality, cardiovascular hospitalization and need for permanent pacemaker implantation in CA-AS patients as compared to lone AS patients undergoing TAVR. Conversely, no differences were found in terms of stroke, acute kidney injury and vascular complications.

Conclusions

Our analysis rejects the idea of futility of TAVR in CA-AS patients showing a clear survival benefit of CA-AS patients undergoing TAVR as compared with medical therapy. Moreover, these patients may undergo TAVR with an acceptable procedural risk, that is substantially comparable to lone AS patients, except for a higher incidence of permanent pacemaker implantation.

Funding Acknowledgement

Type of funding sources: None.

Enhancing AI-guided STEMI detection algorithms by incorporating higher quality fiduciary EKG elements

Background

As EKG interpretation paradigms to a physician-free milieu, accumulating massive quantities of distilled pre-processed data becomes a must for machine learning techniques. In our pursuit of reducing ischemic times in STEMI management, we have improved our Artificial Intelligence (AI)-guided diagnostic tool by following a three-step approach: 1) Increase accuracy by adding larger clusters of data. 2) Increase the breadth of EKG classifications to provide more precise feedback and further refine the inputs which ultimately reflects in better and more accurate outputs. 3) Improving the algorithms' ability to discern between cardiovascular entities reflected in the EKG records.

Purpose

To bolster our algorithm's accuracy and reliability for electrocardiographic STEMI recognition.

Methods

Dataset: A total of 7,286 12-lead EKG records of 10-seconds length with a sampling frequency of 500 Hz obtained from Latin America Telemedicine Infarct Network from April 2014 to December 2019. This included the following balanced classes: angiographically confirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal, and abnormal (200+ CPT codes, excluding the ones included in other classes). Labels of each record were manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: First and last 250 samples were discarded to avoid a standardization pulse. Order 5 digital low pass filters with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: Determined classes were “STEMI” and “Not-STEMI” (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training & Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. Additional testing was performed with a subset of the original complete dataset of unconfirmed STEMI. Performance indicators (accuracy, sensitivity, and specificity) were calculated for each model and results were compared with our previous findings from past experiments.

Results

Complete STEMI data: Accuracy: 95.9% Sensitivity: 95.7% Specificity: 96.5%; Confirmed STEMI: Accuracy: 98.1% Sensitivity: 98.1% Specificity: 98.1%; Prior Data obtained in our previous experiments are shown below for comparison.

Conclusion(s)

After the addition of clustered pre-processed data, all performance indicators for STEMI detection increased considerably between both Confirmed STEMI datasets. On the other hand, the Complete STEMI dataset kept a strong and steady set of performance metrics when compared with past results. These findings not only validate the consistency and reliability of our algorithm but also connotes the importance of creating a pristine dataset for this and any other AI-derived medical tools.

Funding Acknowledgement

Type of funding source: None

Waddling beyond door to balloon times and impinging true ischemic times with artificial intelligence-guided single lead EKG for STEMI detection

Background

The present process of STEMI detection is cumbersome as it utilizes outdated equipment and requires a trained technician and an expert cardiologist. We have developed a patient-administered, Artificial Intelligence (AI) guided, Single Lead EKG for early STEMI detection.

Purpose

To answer the question “Is early STEMI detection possible with a Single Lead EKG?”

Methods

We experimented with an AI-guided algorithm for a single-lead EKG for STEMI detection with the following step-wise developments: 1) An AI algorithm that predictably interprets STEMI using a 12-lead EKG; 2) An AI algorithm for STEMI detection using a single-lead EKG; 3) A methodology for identifying the best single lead to detect STEMI; 4) Advanced AI algorithms for STEMI localization with a single-lead EKG. The AI methodology was as follows: Sample: The mammoth Latin American Telemedicine Infarct Network telemedicine database that provides an umbrella of AMI management to 100 million patients in Brazil, Colombia, Mexico, Chile, and Argentina was queried for cardiologist annotated EKG. A total of 8,511 EKG and 90,592 classified heartbeats were selected for the experiments. Preprocessing: segmentation of each ECG into individual heartbeats. Training & Testing: 90% and 10%, respectively, of the total dataset. Classification: 1-D Convolutional Neural Network; classes were construed for each heartbeat. Performance indicators were calculated per lead.

Results

The algorithm was able to provide an accuracy of 91.9%. Lead V2 yielded the best results among individual leads for STEMI detection.

Conclusions

Early experiments provide a framework for augmenting STEMI detection with the use of AI-guided, single lead techniques. Such approaches seem rational as we target the reduction of true STEMI ischemic times.

Funding Acknowledgement

Type of funding source: None

Maximum artificial intelligence and complete reconstruct of population-based AMI care

Background

After creating a behemoth hub and spoke AMI network that encompasses more than 100 million patients in 5 countries, we have begun to incorporate Artificial Intelligence (AI) algorithms into our telemedicine strategy with the goal of creating comprehensive, very early AMI diagnosis and physician-free triage. In doing so, we have replaced door-to-balloon times (d2b) with symptom-to-balloon times (s2b) as an immutable objective.

Purpose

To incorporate AI attributes for very early AMI detection, triage, and management.

Methods

We expanded our effective telemedicine strategy (100 million population; 877,178 telemedicine encounters; 55% overall mortality reduction; $291 million cost savings) with a logistic reset to impact s2b. To do this, we incorporated our Single Lead 1.0 (lead I) and Single Lead 2.0 (lead V2) technology for self-administered AMI detection with our physician-free STEMI diagnosis and triage AI algorithms. Single Lead algorithms and physician-free protocols were generated by utilizing Machine Learning from our mammoth annotated EKG repository.

Results

In addition to three logistic markers of efficiency Time-to-Telemedicine Diagnosis (TTD), Door-In-Door-Out (DIDO) and Transfer Times (TT); we are monitoring s2b. A gradual release of the algorithms and single lead is occurring at the telemedicine spokes. Detailed results will be available at the time of presentation.

Conclusions

Impacting s2b, the Achilles Heel of Primary PCI, may be achieved with the use of patient-administered AMI detection tools. Incorporation of these technologies into AI algorithms will add to telemedicine efficiencies for population-based AMI care.

Funding Acknowledgement

Type of funding source: None

Moving in sync – concordance betweena artificial intelligence and cardiologist on detecting normal electrocardiograms

Background

Merging modern technologies with classic diagnostic tests often results in a sense of insecurity within the medical community, particularly so with potentially life-saving studies such as the electrocardiogram (EKG). In order to provide a greater sense of trust between Artificial Intelligence (AI) and cardiologists, we provide an AI-driven algorithm capable of accurately and reliably characterize an EKG as normal within a highly complex, cardiologist-reviewed EKG database and report the degree of concordance between this machine vs physician scenario.

Purpose

To provide a dependable and accurate AI algorithm that conducts EKG interpretation in a cardiologist-tier manner.

Methods

The International Telemedical System (ITMS) developed and tested an EKG assessing AI algorithm and incorporated it into the workflow of their Telemedicine Integrated Platform, a digital EKG reading program where cardiologists continuously report their findings remotely in real-time. During the month of April 2,019; 35 ITMS cardiologists reported a grand total of 61,441 EKG records, later submitting them to the AI algorithm implemented through the “One Click Report” process. Through this simple 2-step approach, the algorithm provides a suggestion of “Normal” or “Abnormal” to the cardiologist based on the patterns of the fiducial points included in said EKG reports. Confirmation of these suggestions by the cardiologists ensued.

Results

Overall, cardiologists confirmed 23,213 out of 25,013 AI outputs for “Normal” EKGs, demonstrating a concordance of 92.8% for Normal diagnosis.

Conclusion

Through this methodology, we provide an AI technology that can be reliably applied and trusted in EKG digital platforms to identify and suitably label a normal EKG. Further testing will accrue into a multi label algorithm compatible with abnormal cardiovascular entities, potentially precluding the role of the cardiologist for triaging, particularly in the prehospital setting. We anticipate that this approach will become a promising methodology in modern cardiology practice.

Funding Acknowledgement

Type of funding source: None

Innovative techniques to construct powerful artificial intelligence algorithms for st-elevation myocardial infarction

Background

With the sudden advent of Artificial Intelligence (AI), incorporation of these technologies into key aspects of our working environment has become an ever so delicate task, especially so when dealing with time-sensitive and potentially lethal scenarios such as ST-Elevation Myocardial Infarction (STEMI) management. By further expanding into our successful experiences with AI-guided algorithms for STEMI detection, we implemented an innovative ensemble method into our methodology as we seek to improve the algorithm's predictive capabilities.

Purpose

Through the ensemble method, we combined two ML techniques to boost our previous experiments' accuracy and reliability.

Methods

Database: EKG records obtained from Latin America Telemedicine Infarct Network (Mexico, Colombia, Argentina, and Brazil) from April 2014 to December 2019. Dataset: Two separate datasets were used to train and test two sets of AI algorithms. The first comprised of 11,567 records and the second 7,286 records, each composed of 12-lead EKG records of 10-second length with sampling frequency of 500 Hz, including the following balanced classes: unconfirmed & angiographically confirmed STEMI (first model); angiographically confirmed STEMI only (second model); and, for both models, we included branch blocks, non-specific ST-T abnormalities, normal, and abnormal (200+ CPT codes, excluding the ones included in other classes). Label per record was manually checked by cardiologists to ensure precision (Ground truth). Pre-processing: First and last 250 samples were discarded to avoid a standardization pulse. An order 5 digital low pass filter with a 35 Hz cut-off was applied. For each record, the mean was subtracted to each individual lead. Classification: The determined classes were STEMI and Not-STEMI (A combination of randomly sampled normal, branch blocks, non-specific ST-T abnormalities and abnormal records – 25% of each subclass). Training & Testing: The last dense layer outputs a probability for each record of being STEMI or Not-STEMI. These probabilities were calculated for each model (Model 1 trained with Complete STEMI dataset and Model 2 trained with confirmed STEMI only dataset) and aggregated using the mean aggregation to generate the final label for each record. A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90%/10%; respectively. Results are reported for both testing datasets (Complete and confirmed STEMI only records).

Results

Complete STEMI Dataset: Accuracy: 96.5% Sensitivity: 96.2% Specificity: 96.9% – Confirmed STEMI only Dataset: Accuracy: 98.5% Sensitivity: 98.3% Specificity: 98.6%'

Conclusion(s)

While Model 1 and Model 2 achieved similar performances with promising results on their own, applying a combination of both through the ensemble model exhibits a clear improvement in performance when applied to both datasets. This provides a blueprint for advanced automated STEMI detection through wearable devices.

Funding Acknowledgement

Type of funding source: None

Artificial intelligence methodology: multi-label classification of abnormal EKG records

Background

Our previous experience with Artificial Intelligence (AI)-conducted EKG characterization displayed outstanding results in fast and reliable identification of Normal EKGs within the International Telemedical System (ITMS)'s massive record repository. By expanding the array of recognizable cardiovascular entities, we upgraded our methodology to accurately discriminate an anomaly amongst a highly complex database of EKG records.

Purpose

To present a feasible AI-guided filter that can accurately discriminate and classify Normal and Abnormal EKG records within a multilabeled cardiologist-annotated EKG database.

Methods

ITMS developed and tested the “One Click”' process, a “Normal/Abnormal” EKG assessing AI algorithm, by incorporating it into their digital EKG reading platform where cardiologists continuously report their findings remotely in real time. To ameliorate the diagnostic range of the algorithm, a separate dataset of 121,641 12-lead EKG records was consolidated from the ITMS database from October 2011 to January 2019. Only de-identified data was used. Preprocessing: The first 2s of each short lead and 9s of the long lead were considered. Limb leads I, II and III; and precordial leads V1, V2, V3, and V5 were used. The mean was removed from each lead. AI models/Classification: Two models were created and tested independently based on the method of EKG acquisition (69,852 records transtelephonic [TTP]; 52,259 mobile transmission [MOB]). Each record is categorized into six disjoint classes based on the most common types of cardiac disorders (Low/null co-occurrence pathologies in these datasets were grouped into analogous groups). Training/Testing: Distribution of both sets per transmission type was performed through a greedy algorithm, which identified multiple diagnoses per EKG record and labeled it separately to the corresponding group, ensuring sufficient samples per class. Detailed class distribution is shown below. An inception convolutional neural network was implemented; “Normal” or “Abnormal” labels were assigned to each EKG record independently and were compared to cardiologists' reports; performance indicators were calculated for each model and group.

Results

MOB model accrued an average accuracy of 86.7%; sensitivity of 90.5%; and specificity of 83.9%. TTP model yielded an average accuracy of 77.2%; sensitivity of 91.1%; and specificity of 69.4% (Lower values were attributed to the “Ventricular Complexes” group, which challenged the algorithm by having a smaller ratio of abnormal exams). Detailed results of each training set are shown below.

Conclusion

Providing an effective and reliable multilabel-capable EKG triaging tool remains a challenging but attainable goal. Continuous systematic enhancement of our AI-driven methodology has led us to satisfactory, yet imperfect results which compel us to further study and improve our efforts to provide a trustworthy cardiologist-friendly triage device.

Funding Acknowledgement

Type of funding source: None

Change in renal function post-nephrectomy for renal cell carcinoma in patients with and without hypertension and/or diabetes

BACKGROUND

The standard of care for surgically resectable disease renal cell carcinoma (RCC) is a nephrectomy. Post-nephrectomy, these patients are at risk for the development of new onset chronic kidney disease or the progression of pre-existing chronic kidney disease. We aimed to report the changes in renal function in patients who had a nephrectomy for RCC.

METHODS

This retrospective, descriptive, cross-sectional study identified 137 patients who had a nephrectomy for RCC from 1 January 2009 to 31 December 2017. The pre-nephrectomy and post-nephrectomy estimated glomerular filtration rate (eGFR) and the histological subtype of RCC on histopathological analysis of the resected specimen were recorded from the National Health Laboratory Services online results platform. All analyses were conducted using SPSS (Version 25) and the significance level was set at p < 0.05.

RESULTS

After a mean follow-up period of 26.5 ± 22 months (median = 19 months), the patients' eGFR dropped by a mean of 4.82 ± 8.67 ml/min/1.73 m2 (95% CI 3.23-6.41) post-nephrectomy. The mean eGFR fall in patients' who had hypertension and/or diabetes (n = 63) was significantly larger compared to patients who had neither of these comorbidities (n = 54; p < .001; mean = 7.30 ± 8.40 ml/min/1.73 m2 (95% CI 5.19-9.42) and 1.93 ± 8.14 ml/min/1.73 m2 (95% CI 0.30-4.15) respectively.

CONCLUSIONS

The decline in renal function in patients with hypertension and/or diabetes mellitus is more pronounced than in patients with neither of these comorbidities. In these high-risk patients, measures must be taken to prevent the development and limit the progression of chronic kidney disease.

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.

P1524Women are from venus and face barriers for AMI treatment

Background

The Latin American Telemedicine Infarct Network (LATIN), a program for managing population-based AMI care, has utilized an innovative hub-spoke strategy and remote guidance to expand medical access in remote parts of Brazil, Colombia, Mexico, and Argentina. Based on the Global Lumen Organization for Women (GLOW) project, that has previously demonstrated gender inequalities and worse outcomes for women who undergo Primary PCI, our research explored the management of female patients in our network.

Purpose

To demonstrate gender disparities in a telemedicine-guided, population based AMI program.

Methods

Meta-analysis of >750,000 patients within LATIN. Telemedicine was employed as a screening tool to accurately diagnose AMI. According to the duration of chest pain and transfer time, AMI patients were triaged into guidelines-based pathways of thrombolysis, pharmaco-invasive management or Primary PCI. Resource allocation was identical for men and women.

Results

Data from 784,395 screened patients reveals broad gender disparities. The critical results yielded that female patients have a lower prevalence of STEMI diagnosis and treatment regardless of the technique – PCI, pharmaco-invasive or CABG (p<0.01). These findings assume more significance given the fact that more women than men, were screened through the Telemedicine pathway.

Conclusions

LATIN gender data signals the urgency to demand better AMI care for women.

P3352Telemedicine transcends national boundaries in quest of creating a behemoth ami program

Background

The Latin America Telemedicine Infarct Network (LATIN) has exploited the remarkable competence of telemedicine for remote guidance. In doing so, LATIN created a mammoth population-based AMI network that employed experts located several hundred miles away to guide the reperfusion strategies for almost 800,000 screened patients. In this pioneering project, telemedicine was initially utilized to guide AMI management within national confines. We speculated whether LATIN telemedicine navigation could outstrip countrywide borders.

Purpose

To maximally harness the vast possibilities of telemedicine for improving AMI care.

Methods

During its pilot phase, LATIN began as a hub and spoke, AMI system in Colombia where 20 spokes (small community health centers and rural clinics) were configured with 3 hubs that could perform Primary PCI. These sites were linked through web-based connectivity. Expert cardiologists, located 50–250 miles away in Bogota, Colombia, used sophisticated telemedicine platforms for urgent EKG diagnosis and teleconsultation of the entire AMI process. Based upon the duration of chest pain and travel time to the hub, these experts guided patients through guideline-based strategies of thrombolysis, pharmaco invasive management or primary PCI. Efficiency of the telemedicine process was measured with the new metric of time to telemedicine diagnosis (TTD). Cloud computing, GPS navigation, and numerous business intelligent tools were gradually incorporated into LATIN telemedicine. As systems became more scalable, the program was expanded to Brazil, where LATIN flourished. Over the last 18 months, LATIN telemedicine capabilities have been pressed across national boundaries. Presently, all 82 LATIN centers in Mexico are guided by experts located in Bogota, Colombia and the 7 Argentina centers channeled through Santiago, Chile.

Results

784,947 patients were screened for AMI at 350 LATIN centers (Brazil 143, Colombia 118, Mexico 82, Argentina 7). Navigation pathways are depicted in the attached figure. TTD remains extremely low in all four countries, and comparable efficiency and tele-accuracy have been achieved. With expanded geographic reach, 8,448 (1.08%) patients were diagnosed with STEMI and 3,911 (46.3%) urgently reperfused, including 3,049 (78%) with Primary PCI. Time to TTD ranged between 2.8 to 5.8 minutes, with a mean of 3.5 min. Tele-accuracy was 98.5%, D2B 51 min, and in-hospital mortality 5.2%. Various other comparative metrics for the 4 countries are being gathered and will be available at the time of presentation.

Conclusions

LATIN demonstrates the robust ability of telemedicine to transcend national boundaries to guide AMI management. This strategy can be adopted in under-developed countries in Asia and Africa to provide an umbrella of AMI care for the millions of disadvantaged patients.

P6417Increasing the accuracy of a machine learning algorithm for STEMI diagnosis by incorporating demographic variables

Background

Our previous work demonstrated the diagnostic value of Artificial Intelligence (AI) -driven algorithms for ST-Elevation Myocardial Infarction (STEMI). In the present research, we explore the importance of demographic data inclusion, in order to achieve a more accurate diagnosis.

Purpose

To demonstrate that incorporation of demographic variables into the sample records will augment the accuracy of AI-based protocols for STEMI diagnosis.

Methods

An observational, retrospective, case-control study. Demographic data (age and gender) male/female ratio 1.3, ages 98–18 years was added to the sample records. Sample: 8,511 EKG records, previously diagnosed as normal, abnormal (over 200 conditions) or STEMI. 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 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 was used, respectively. Experiments: Intel PC i7 8750H processor at 2.21GHz, 16GB RAM, Windows 10 OS with Nvidia GTX 1070GPU, 8GB RAM.

Results

The model yielded an accuracy of 97.1%, a sensitivity of 96.8%, and a specificity of 97.5%.

Conclusions

The ability of AI-guided algorithms to diagnose STEMI is increased by expanding the morphological variables with demographic data. This approach may be applied to improve the EKG diagnosis of other cardiovascular entities and improve clinical management.

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.

P2426Validating the diagnostic value of a machine learning algorithm for STEMI detection

Background

We have previously reported the use of Artificial Intelligence (AI) guided EKG analysis for detection of ST-Elevation Myocardial Infarction (STEMI). To demonstrate the diagnostic value of our algorithm, we compared AI predictions with reports that were confirmed as STEMI.

Purpose

To demonstrate the absolute proficiency of AI for detecting STEMI in a standard12-lead EKG.

Methods

An observational, retrospective, case-control study. Sample: 5,087 EKG records, including 2,543 confirmed STEMI cases obtained via feedback from health centers following appropriate patient management (thrombolysis, primary Percutaneous Coronary Intervention (PCI), pharmacoinvasive therapy or coronary artery bypass surgery). Records excluded patient and medical information. The sample was derived from the 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 (53,667 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 yielded an accuracy of 97.2%, a sensitivity of 95.8%, and a specificity of 98.5%.

Conclusion(s)

Our AI-based algorithm can reliably diagnose STEMI and will preclude the role of a cardiologist for screening and diagnosis, especially in the pre-hospital setting.

P575Merging technologies to provide Mexico an innovative nationwide AMI management network

Background

“Cόdigo Infarto”, the vast patient-centric, app-based, educational crusade of the Mexican Society of Interventional Cardiology (SOCIME) has been combined with the Latin America Telemedicine Infarct Network (LATIN) to create a comprehensive, national AMI program for Mexico.

Purpose

To demonstrate the benefits of amalgamating educational initiatives of national cardiology societies with a global telemedicine program for improving AMI management.

Methods

“Cόdigo Infarto” App connects patients to a network of several hundred cardiologists and 250 Primary PCI-capable labs. LATIN provides the partnership with its robust telemedicine platform, a hub-spoke strategy that supports patient's access to appropriate medical management. Remotely located experts, in Colombia, provide urgent EKG diagnosis via tele-consultation to the entire LATIN Mexico network. They activate ambulance dispatch and implement guideline-based protocols.

Results

Numerous “Cόdigo Infarto” sites have incorporated LATIN to provide a simple and accelerated management of AMI patients. Currently, the partnership (7 hubs, 78 spokes) has screened 19,886 patients. A total of 359 STEMI cases (1.8%) have been diagnosed; 118 patients (33%) were urgently reperfused, Primary PCI was performed in 74% of the latter cases. D2B time was 41 min. Reasons for the lack of treatment include delayed presentation, lack of ICU beds and insurance denials. Currently, these constraints are being methodically probed. Updated results will be available at time of presentation.

Conclusions

The synergy of the AMI initiative for Mexico provides a template for similar initiatives in developing countries.

Laparoscopic sleeve gastrectomy for morbid obesity: role of intraluminal and intraperitoneal postoperative drainage

BACKGROUND AND AIMS

Bleeding and staple line leak are the most common postoperative complications of LSG. To prevent and/or to promptly identify such complications, conventional peri-operative protocols imply post-operative gastric decompression (NGT) and staple line drain (IAD). Our aim was to evaluate the role of naso-gastric tube (NGT) and intra-abdominal drain (IAD) in preventing and/or facilitating identification and treatment of post-operative complications after sleeve gastrectomy.

PATIENTS AND METHODS

A retrospective observational study on two consecutive series has been undertaken to evaluate the real utility of routine placement of NGT and IAD at the end of a LSG to prevent (primary end-point), promptly identify (secondary end-point) and manage (tertiary end-point) bleeding and staple line leakage. Collected outcome data of all consecutive cases, which underwent primary LSG at our Department, were analyzed. The first 100 consecutive patients (group A) received the standard perioperative protocol and the other consecutive 100 (group B) received a fast track protocol (no NGT neither IAD).

RESULTS

The two groups were not different in their outcome. Two bleeding occurred in Group A and were conservatively treated. One abscess developed in group B soon after surgery. It was diagnosed by an abdominal CT performed because patients presented fever, leucocitosis and tachycardia. It was successfully treated by percutaneous ultrasound-guided drainage. One fistula occurred in group B after discharge on 30th post-operative day. Fistula was suspected based on fever and tachycardia in absence of any abdominal discomfort and was confirmed by an abdominal CT. The patient was successfully treated in 40 days by endoscopic positioning of a gastric tube-prosthesis and percutaneous ultrasound-guided drainage of abdominal collection. A third patient in group B experienced bleeding suspected due to hemoglobin drop and confirmed by abdominal CT. He also was conservatively treated.

CONCLUSIONS

In conclusion, placement of drains does not facilitate detection of leak, abscess, or bleeding after primary LSG.

Seroepidemiological Studies of Arboviruses in Africa

The literature on sero-epidemiological studies of flaviviral infections in the African continent is quite scarce. Much of the viral epidemiology studies have been focussing on diseases such as HIV/AIDS because of their sheer magnitude and impact on the lives of people in the various affected countries. Increasingly disease outbreaks caused by arboviruses such as the recent cases of chikungunya virus, dengue virus and yellow fever virus have prompted renewed interest in studying these viruses. International agencies from the US, several EU nations and China are starting to build collaborations to build capacity in many African countries together with established institutions to conduct these studies. The Tofo Advanced Study Week (TASW) was established to bring the best scientists from the world to the tiny seaside town of Praia do Tofo to rub shoulders with African virologists and discuss cutting-edge science and listen to the work of researchers in the field. In 2015 the 1st TASW focussed on Ebola virus. The collections of abstracts from participants at the 2nd TASW which focused on Dengue and Zika virus as well as presentations on other arboviruses are collated in this chapter.

Impact of transitional care on endocrine and anthropometric parameters in Prader-Willi syndrome

CONTEXT

The transition of patients with Prader-Willi syndrome (PWS) to adult life for medical care is challenging because of multiple comorbidities, including hormone deficiencies, obesity and cognitive and behavioral disabilities.

OBJECTIVE

To assess endocrine management, and metabolic and anthropometric parameters of PWS adults who received (n = 31) or not (n = 64) transitional care, defined as specialized pediatric care followed by a structured care pathway to a multidisciplinary adult team.

PATIENTS AND STUDY DESIGN

Hormonal and metabolic parameters were retrospectively recorded in 95 adults with PWS (mean ± s.d. age 24.7 ± 8.2 years, BMI: 39.8 ± 12.1 kg/m²) referred to our Reference Center and compared according to transition.

RESULTS

Among the entire cohort, 35.8% received growth hormone (GH) during childhood and 16.8% had a GH stimulation test after completion of growth. In adulthood, 14.7% were treated with GH, 56.8% received sex-hormone therapy, whereas 91.1% were hypogonadic and 37.9% had undergone valid screening of the corticotropic axis. The main reason for suboptimal endocrine management was marked behavioral disorders. Patients receiving transitional care were more likely to have had a GH stimulation test and hormonal substitutions in childhood. They also had a lower BMI, percentage of fat mass, improved metabolic parameters and fewer antidepressant treatments. Transitional care remained significantly associated with these parameters in multivariate analysis when adjusted on GH treatment.

CONCLUSION

A coordinated care pathway with specialized pediatric care and transition to a multidisciplinary adult team accustomed to managing complex disability including psychiatric troubles are associated with a better health status in adults with PWS.

Kaolin modulates ABA and IAA dynamics and physiology of grapevine under Mediterranean summer stress

The foliar exogenous application of kaolin, a radiation-reflecting inert mineral, has proven to be an effective short-term climate change mitigation strategy for Mediterranean vineyards. In this work, we address the hypothesis that kaolin could improve both the hormonal dynamics and physiological responses of grapevines growing in Douro Region, northern Portugal. For this purpose, the leaf water potential, gas exchange and chlorophyll a fluorescence parameters were monitored, as well as the abscisic acid (ABA) and indole-3-acetic acid (IAA) quantification and immunolocalization were assessed. The study revealed a slight decrease in ABA and an increase in IAA in the kaolin treatment, which in turn were associated with the improvement of physiological performance. A month after spraying, kaolin improves the water potential respectively, 30% and 17% in the predawn and midday periods. Besides, plants treated with kaolin showed higher values of stomatal conductance, net CO₂ assimilation rate and intrinsic water use efficiency. Kaolin also ameliorates the effective PSII efficiency (67%), as well as the maximum quantum efficiency of photosystem II and the photosynthetic electron transport rate (>73%). These results were consistent with the higher photochemical quenching and the lower non-photochemical quenching observed in treated leaves and with the better performance obtained by the JIP test parameters. Physiological and hormonal analysis confirmed that kaolin effectively enhance grapevine summer stress tolerance.

Cyto- and genotoxic profile of groundwater used as drinking water supply before and after disinfection

The assessment of the toxicological properties of raw groundwater may be useful to predict the type and quality of tap water. Contaminants in groundwater are known to be able to affect the disinfection process, resulting in the formation of substances that are cytotoxic and/or genotoxic. Though the European directive (98/83/EC, which establishes maximum levels for contaminants in raw water (RW)) provides threshold levels for acute exposure to toxic compounds, the law does not take into account chronic exposure at low doses of pollutants present in complex mixture. The purpose of this study was to evaluate the cyto- and genotoxic load in the groundwater of two water treatment plants in Northern Italy. Water samples induced cytotoxic effects, mainly observed when human cells were treated with RW. Moreover, results indicated that the disinfection process reduced cell toxicity, independent of the biocidal used. The induction of genotoxic effects was found, in particular, when the micronucleus assay was carried out on raw groundwater. These results suggest that it is important to include bio-toxicological assays as additional parameters in water quality monitoring programs, as their use would allow the evaluation of the potential risk of groundwater for humans.

Abstract P5-17-10: Claudin -4 expression in carcinoma in situ and its association with local recurrence, clinical and immunohistochemistry characteristics

Introduction: Claudins are tight junction molecules and have been associated to breast cancer prognosis. Claudin-low intrinsic subtype of invasive carcinoma was described recently and has been related to high grade carcinoma, low junction molecules expression and worse chemotherapy response. However, it is unknown whether Claudins expression could be associated to carcinoma in situ prognostic. The aim of this study was evaluated the Claudin – 4 expression in carcinoma in situ and its association with local recurrence, clinical and immunohistochemistry characteristics.

Methods: A tissue microarray (TMA) block was constructed, using region of interesting, with 137 pure carcinoma in situ paraffin blocks of patients treated in the Women 's Hospital Prof. Dr. José Aristodemo Pinotti – UNICAMP from 1999 to 2009. The TMA was submitted to immunohistochemistry analyze to: Claudin-4, beta-catenin, e-caderin, estrogen receptor (ER), progesterone receptor (PR), HER-2 and Ki-67. It was calculated Claudin-4 score based in percentage and intensity of expression and categorized in: Claudin-4 low and Claudin – 4 high. The clinical data, treatment data (surgery, radiotherapy and tamoxifen use), local recurrence data (date and type) and death of each patient were reviewed in the medical records. The statistical analyze used Kaplan-Meier curve and log-rank test to disease free survival; qui-square and Fisher test to compare others variables; significance level of 5 % was used.

Results: It was possible to evaluate Claudin-4 expression in 86 cases, 88.4% were Claudin-4 high and 11.6% Claudin-4 low. The follow up mean was 69 months and local recurrence rate was 10.5 %. There was no significant difference in local recurrence rate between Claudin-4 high and Claudin-4 low (10.0% x 10.5% , p=1.0).The disease free survival was similar between Claudin-4 low and Claudin-4 high (p=0.559). The Claudin- 4 high was significantly more frequent in beta-catenin positive patients (p=0.048). There was no association significantly between Claudin-4 expression and: age (p=0.66), histology type (p=0.75), surgery (p=0.102), radiotherapy (p=0.29), tamoxifen use (p=0.432), ER (p=0.33), PR (p=1.0), HER-2 (p=0.23) and e-caderin (p=0.21).

Conclusion: Despite the Claudins are related to invasive carcinoma prognosis, our outcome did not show difference in local recurrence and disease free survival between Claudin-4 low and high in carcinoma in situ. The beta-catenin and claudin-4 expressions were significantly associated.

Citation Format: Duarte GM, Toucchet F, Espinola JP, Barreto CR, Paiva Silva GR, Almeida NR, Soares F, Pinto G, Marshall P. Claudin -4 expression in carcinoma in situ and its association with local recurrence, clinical and immunohistochemistry characteristics. [abstract]. In: Proceedings of the Thirty-Eighth Annual CTRC-AACR San Antonio Breast Cancer Symposium: 2015 Dec 8-12; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2016;76(4 Suppl):Abstract nr P5-17-10.

Characterization and prevalence of severe primary IGF1 deficiency in a large cohort of French children with short stature

OBJECTIVE

The prevalence of severe primary IGF1 deficiency (IGFD) is unclear. IGFD must be identified promptly as treatment with recombinant human IGF1 (rhIGF1) is now available. Our objective was to characterize and assess the prevalence of severe primary IGFD in a large cohort of patients evaluated for short stature at a pediatric endocrinology unit in France.

DESIGN

Observational study in a prospective cohort.

METHODS

Consecutive patients referred to our unit between 2004 and 2009 for suspected slow statural growth were included. Patients were classified into eight etiological categories. IGFD was defined by height ≤-3 SDS, serum IGF1 levels <2.5th percentile, GH sufficiency, and absence of causes of secondary IGFD.

RESULTS

Out of 2546 patients included, 337 (13.5%) were born small for gestational age and 424 (16.9%) had idiopathic short stature. In these two categories, we identified 30 patients who met our criterion for IGFD (30/2546, 1.2%). In these 30 patients, we assessed the response to IGF1 generation test, time course of IGF1 levels, and efficiency of GH replacement therapy. The results indicated that only four of the 30 children were definite or possible candidates for rhIGF1 replacement therapy.

CONCLUSION

The prevalence of severe primary IGFD defined using the standard criterion for rhIGF1 treatment was 1.2%, and only 0.2% of patients were eligible for rhIGF1 therapy.

Unexpected high frequency of skeletal dysplasia in idiopathic short stature and small for gestational age patients

OBJECTIVE

To assess the prevalence of skeletal dysplasias (SDs) in patients with idiopathic short stature (ISS) or small for gestational age (SGA) status.

SETTING

Rare Endocrine/Growth Diseases Center in Paris, France.

DESIGN

A prospective study on consecutive patients with ISS and SGA enrolled from 2004 to 2009.

METHOD

We used a standardized workup to classify patients into well-established diagnostic categories. Of 713 patients with ISS (n=417) or SGA status (n=296), 50.9% underwent a skeletal survey. We chose patients labeled normal or with a prepubertal slowdown of growth as a comparison group.

RESULTS

Diagnoses were ISS (16.9%), SGA (13.5%), normal growth (24.5%), transient growth rate slowing (17.3%), endocrine dysfunction (12%), genetic syndrome (8.9%), chronic disease (5.1%), and known SD (1.8%). SD was found in 20.9% of SGA and 21.8% ISS patients and in only 13.2% in our comparison group. SD prevalence was significantly higher in the ISS group than in the comparison group, especially (50%) for patients having at least one parent whose height was <-2 SDS. Dyschondrosteosis and hypochondroplasia were the most frequently identified SD, and genetic anomaly was found in 61.5 and 30% respectively. Subtle SD was found equally in the three groups and require long-term growth follow-up to evaluate the impact on final height.

CONCLUSION

SD may explain more than 20% of cases of growth retardation ascribed to ISS or SGA, and this proportion is higher when parental height is <-2 SDS. A skeletal survey should be obtained in patients with delayed growth in a context of ISS or SGA.

Childhood craniopharyngioma: hypothalamus-sparing surgery decreases the risk of obesity

CONTEXT

Craniopharyngioma is a brain tumor whose high local recurrence rate has for a long time led to a preference for extensive surgery. Limited surgery minimizing hypothalamic damage may decrease the severe obesity rate at the expense of the need for radiotherapy to complete the treatment.

OBJECTIVE

We compared weight gain and local recurrence rates after extensive resection surgery (ERS) and hypothalamus-sparing surgery (HSS).

DESIGN

Our observational study compared a historical cohort managed with ERS between 1985 and 2002 to a prospective cohort managed with HSS between 2002 and 2010.

SETTING

The patients were treated in a pediatric teaching hospital in Paris, France.

PATIENTS

Thirty-seven boys and 23 girls were managed with ERS (median age, 8 years); 38 boys and 27 girls were managed with HSS (median age, 9.3 years).

MAIN OUTCOME MEASURES

Data were collected before and 6 months to 7 years after surgery. Body mass index (BMI) Z-score was used to assess obesity and the number of surgical procedures to assess local recurrence rate.

RESULTS

Mean BMI Z-score before surgery was comparable in the 2 cohorts (0.756 after ERS vs 0.747 after HSS; P = .528). At any time after surgery, mean BMI Z-score was significantly lower after HSS (eg, 1.889 SD vs 2.915 SD, P = .004 at 1 year). At last follow-up, the HSS cohort had a significantly lower prevalence of severe obesity (28% vs 54%, P < .05) and higher prevalence of normal BMI (38% vs 17%, P < .01). Mean number of surgical procedures was not significantly different in the 2 cohorts.

CONCLUSIONS

Hypothalamus-sparing surgery decreases the occurrence of severe obesity without increasing the local recurrence rate.