O12 Artificial intelligence-based risk prediction for death after emergency laparotomy using multi slice contrast enhanced computerised tomography

2021 ◽  
Vol 108 (Supplement_5) ◽  
Author(s):  
S Rahman ◽  
S Body ◽  
M Ligthart ◽  
P May-Miller ◽  
P Pucher ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Risk Prediction ◽  
Automated Analysis ◽  
Mortality Prediction ◽  
Elastic Net ◽  
Emergency Laparotomy ◽  
Cross Sectional ◽  
Post Surgery ◽  
Preoperative Ct ◽  
Clinical Tools

Abstract Introduction Emergency laparotomy has a considerable mortality risk, with more than one in ten patients not surviving to discharge. Preoperative risk prediction using clinical tools is well established, however implemented variably. Preoperative CT is undertaken almost universally and contains granular data beyond diagnostics, including body composition, disease severity and other abstract features with the potential to enhance risk prediction. In this study we established the value of features extracted in an automated fashion from pre-operative CT in predicting 90-day post-surgery mortality. Method Anonymised CTs were collated from patients undergoing emergency laparotomy at ten hospitals in Southern England (2016–2017). For each case, axial portal venous abdominal/pelvic series were analysed using a pre-trained neural network, with each image converted into a matrix of numerical features. An elastic-net regression model to predict 90-day mortality was trained using these features and evaluated by bootstrapping with 1000 resampled datasets. Result A total of 136,709 images from 274 cases were available for analysis with a mean of 503 per case. Mortality within 90 days occurred in 34 cases (12.4%) with an average NELA mortality prediction of 8.5%. On internal (bootstrap) validation, the elastic net model derived from CT yielded excellent performance (AUC 0.903 95%CI 0.897–0.909), significantly in excess of the NELA risk calculator (AUC 0.809 95%CI 0.736–0.875), with a broader prediction range (0.01%-89.71%). Conclusion Artificial intelligence techniques applied to routinely performed cross-sectional imaging predicts emergency laparotomy mortality with greater accuracy than clinical data alone. Integration of these automated tools may be possible in the future. Take-home Message Automated analysis of CT can accurately predict risk of mortality after emergency laparotomy.

Psychological distress in patients undergoing urological surgery: A cross-sectional study

2021 ◽  
pp. 205141582110140
Author(s):  
Nuala Murray ◽  
Charles O’Connor ◽  
Rhona Dempsey ◽  
Sean Liew ◽  
Helen Richards ◽  
...  
Keyword(s):  
Psychological Distress ◽  
Repeated Measures ◽  
Depression Scale ◽  
University Hospital ◽  
Anxiety And Depression ◽  
Hospital Anxiety ◽  
Level Of Evidence ◽  
Cross Sectional ◽  
Post Surgery ◽  
Oncological Patients

Purpose: The purpose of this study was to evaluate the psychological distress of urological and uro-oncological patients undergoing surgery. Methods: Patients who presented to Mercy University Hospital from October 2019–May 2020 were consecutively recruited. Demographic and clinical characteristics including age, gender, marital status, type of surgery (uro-oncology or general urology), endoscopy or open surgery were gathered. Mood was evaluated using the Hospital Anxiety and Depression Scale prior to admission, prior to discharge and 6 weeks post-surgery. Results: A total of 118 participants (79.7% male) completed the Hospital Anxiety and Depression Scale prior to admission, prior to discharge and at 6 weeks post-surgery. Forty patients (33.9%) underwent uro-oncology-related surgery. At pre-admission 39 patients (33%) fell into a possible-probable clinical category for anxiety and 15 (12.7%) for depression. Older patients had significantly lower anxiety levels than younger patients ( p⩽0.01). There were no differences between patients undergoing uro-oncology or more general urology surgery and levels of anxiety or depression. Repeated measures analysis of variance with age as a covariate indicated no significant differences in Hospital Anxiety and Depression Scale anxiety scores over time. There was a statistically significant reduction in Hospital Anxiety and Depression Scale depression scores over the three assessment time points ( p=0.004). Conclusion: Over one-third of patients were experiencing moderate to severe levels of psychological distress pre-surgery – higher than levels previously reported in uro-oncological patients. Surprisingly, there was no difference in anxiety and depression scores in uro-oncology and urology patients. Psychological distress in both uro-oncology and more general urology patients should be considered in the surgical setting. Level of evidence Moderate

scholarly journals Comparison of predicted psychological distress among workers between artificial intelligence and psychiatrists: a cross-sectional study in Tsukuba Science City, Japan

BMJ Open ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. e046265
Author(s):  
Shotaro Doki ◽  
Shinichiro Sasahara ◽  
Daisuke Hori ◽  
Yuichi Oi ◽  
Tsukasa Takahashi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Psychological Distress ◽  
Cross Sectional Study ◽  
Sectional Study ◽  
Cross Sectional ◽  
Explanatory Variables ◽  
The Neural Network ◽  
Significant Difference ◽  
Total Data

ObjectivesPsychological distress is a worldwide problem and a serious problem that needs to be addressed in the field of occupational health. This study aimed to use artificial intelligence (AI) to predict psychological distress among workers using sociodemographic, lifestyle and sleep factors, not subjective information such as mood and emotion, and to examine the performance of the AI models through a comparison with psychiatrists.DesignCross-sectional study.SettingWe conducted a survey on psychological distress and living conditions among workers. An AI model for predicting psychological distress was created and then the results were compared in terms of accuracy with predictions made by psychiatrists.ParticipantsAn AI model of the neural network and six psychiatrists.Primary outcomeThe accuracies of the AI model and psychiatrists for predicting psychological distress.MethodsIn total, data from 7251 workers were analysed to predict moderate and severe psychological distress. An AI model of the neural network was created and accuracy, sensitivity and specificity were calculated. Six psychiatrists used the same data as the AI model to predict psychological distress and conduct a comparison with the AI model.ResultsThe accuracies of the AI model and psychiatrists for predicting moderate psychological distress were 65.2% and 64.4%, respectively, showing no significant difference. The accuracies of the AI model and psychiatrists for predicting severe psychological distress were 89.9% and 85.5%, respectively, indicating that the AI model had significantly higher accuracy.ConclusionsA machine learning model was successfully developed to screen workers with depressed mood. The explanatory variables used for the predictions did not directly ask about mood. Therefore, this newly developed model appears to be able to predict psychological distress among workers easily, regardless of their subjective views.

scholarly journals Contributions of PCSS, CISS, and VOMS for Identifying Vestibular/Ocular Motor Deficits in Pediatric Concussions

2021 ◽  
pp. 194173812199411
Author(s):  
Rishi D. Patel ◽  
Cynthia R. LaBella
Keyword(s):  
Sports Medicine ◽  
Tertiary Care ◽  
Motor Dysfunction ◽  
Motor Deficits ◽  
Ocular Motor ◽  
Symptom Scale ◽  
Level Of Evidence ◽  
Cross Sectional ◽  
Visual Problems ◽  
Clinical Tools

Background: Vestibular/ocular motor dysfunction can occur in pediatric concussions, which can impair reading, learning, and participation in athletics. This study evaluated 3 clinical tools for identifying postconcussion vestibular/ocular motor dysfunction: (1) Post-Concussion Symptom Scale (PCSS), (2) Convergence Insufficiency Symptom Survey (CISS), and (3) Vestibular/Ocular Motor Screening (VOMS). Hypothesis: Evaluating vestibular/ocular motor dysfunction with multiple clinical tools will capture more symptomatic patients than any 1 tool alone. Study Design: Cross-sectional data from a prospective cohort study. Level of Evidence: Level 4. Methods: Patients were between 8 and 17 years old and seen in a tertiary care pediatric sports medicine clinic between August 2014 and February 2018. Data were collected from initial visit and included VOMS, PCSS, and CISS. Descriptive statistics, Pearson’s correlations, and logistic regressions were used to describe relationships between clinical tools. Results: Of the 156 patients (55.1% female; 14.35 ± 2.26 years old) included, this study identified 129 (82.7%) with vestibular/ocular motor dysfunction. Of these 129, 65 (50.4%) reported “visual problems” on PCSS, 93 (72.1%) had abnormal CISS, and 99 (76.7%) had abnormal VOMS. Together, VOMS and CISS identified 64 (49.6%) patients without reported “visual problems” on PCSS. Higher total PCSS scores predicted abnormal CISS (odds ratio [OR], = 1.11; 95% CI, 1.07-1.17) and abnormal VOMS (OR, 1.03; 95% CI, 1.01-1.06). “Visual problems” on PCSS did not predict abnormal CISS or VOMS. Conclusions: Vestibular/ocular motor dysfunction were identified in nearly 83% of study subjects when PCSS, CISS, and VOMS are used together. Clinical Relevance: These results suggest adding CISS and VOMS to the clinical evaluation of concussions can help clinicians identify post-concussion vestibular/ocular motor dysfunction.

An Artificial Intelligence Tool for Image Simulation in Rhinoplasty

2021 ◽  
Author(s):  
Hernan Chinsk ◽  
Ricardo Lerch ◽  
Damián Tournour ◽  
Luis Chinski ◽  
Diego Caruso
Keyword(s):  
Artificial Intelligence ◽  
Survey Study ◽  
P Value ◽  
Cross Sectional Survey ◽  
Simulated Image ◽  
Level Of Evidence ◽  
Cross Sectional ◽  
Partial Agreement ◽  
Aesthetic Rhinoplasty ◽  
Level Of Agreement

AbstractDuring rhinoplasty consultations, surgeons typically create a computer simulation of the expected result. An artificial intelligence model (AIM) can learn a surgeon's style and criteria and generate the simulation automatically. The objective of this study is to determine if an AIM is capable of imitating a surgeon's criteria to generate simulated images of an aesthetic rhinoplasty surgery. This is a cross-sectional survey study of resident and specialist doctors in otolaryngology conducted in the month of November 2019 during a rhinoplasty conference. Sequential images of rhinoplasty simulations created by a surgeon and by an AIM were shown at random. Participants used a seven-point Likert scale to evaluate their level of agreement with the simulation images they were shown, with 1 indicating total disagreement and 7 total agreement. Ninety-seven of 122 doctors agreed to participate in the survey. The median level of agreement between the participant and the surgeon was 6 (interquartile range or IQR 5–7); between the participant and the AIM it was 5 (IQR 4–6), p-value < 0.0001. The evaluators were in total or partial agreement with the results of the AIM's simulation 68.4% of the time (95% confidence interval or CI 64.9–71.7). They were in total or partial agreement with the surgeon's simulation 77.3% of the time (95% CI 74.2–80.3). An AIM can emulate a surgeon's aesthetic criteria to generate a computer-simulated image of rhinoplasty. This can allow patients to have a realistic approximation of the possible results of a rhinoplasty ahead of an in-person consultation. The level of evidence of the study is 4.

Abstract 17979: Left Atrial Cross Sectional Area is a Novel Echocardiographic Measure Which Improves the Predictive Value of Chads2 Score in Risk Stratification of Cardioembolic Strokes

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Timothy C Tan ◽  
Mark Handschumacher ◽  
Octavio M Pontes-Neto ◽  
Maria C Nunes ◽  
Yong H Park ◽  
...  
Keyword(s):  
Risk Stratification ◽  
Risk Prediction ◽  
Left Atrial ◽  
Stroke Risk ◽  
Thrombus Formation ◽  
Cross Sectional Area ◽  
Sectional Area ◽  
Chads2 Score ◽  
Cross Sectional ◽  
C Statistic

Background: Cardioembolic (CE) stroke carries significant morbidity and mortality. Current risk stratification tools such as CHADS2 score do not include any imaging parameters and are based on clinical features, which have limitations. Left atrial (LA) enlargement and remodeling may be associated with CE risk due to predisposition for atrial arrhythmias and thrombus formation. Left atrial cross sectional area (LACSA), a novel echo measure which reflects both LA size and shape, may improve CE stroke risk assessment. Aim: This study examined the value of LACSA in predicting CE stroke risk and the improvement in risk prediction when added to CHADS2 score. Methods: Clinical and echo parameters were examined in a prospective cohort of 1275 consecutive patients with ischemic stroke. Strokes were classified using the Causative Classification of Strokes and 259 (20%) were classified as CE stroke. LACSA was calculated using the formula: π/4*largest measured LA diameter*smallest measured LA diameter where mid LA diameter was measured in the parasternal long axis, 4 chamber and 2 chamber views. Results: Patients with CE stroke had greater LACSA (8.6 ± 2.3 vs 6.4 ± 1.8 cm2/m2; p<0.001) and mean CHADS2 score (2.25 ± 1.28 vs 1.87 ± 1.40; p<0.0001) compared to non-CE stroke patients. LACSA was independently associated with CE strokes (OR 1.21; 95% CI 1.08-1.34; p=0.001) in a multivariable model adjusted for CHADS2, gender, score, BMI, atrial fibrillation, anti-platelet and anti-coagulant use, E/E’ and LVEF. The addition of LACSA to CHADS2 score improved the prediction of CE stroke (c-statistic for predicting CE stroke using CHADS2 alone was 0.59 (95% CI 0.55-0.63) vs CHADS2 and LACSA 0.78 (95% CI 0.72-0.80) (p<0.001). Conclusion: LACSA is a novel measure of LA remodeling and associated with CE stroke. LACSA, an imaging parameter, enhances the risk prediction of the CHADS2 score, a clinical measure of risk, improving risk stratification for CE stroke and impacting therapeutic strategies.

scholarly journals Gambaran disfungsi ereksi pada pasien dengan benign prostatic hyperplasia (BPH) di Klinik Advent Tikala Manado

2016 ◽  
Vol 4 (2) ◽  
Author(s):  
Michael B. Tawale ◽  
Lydia Tendean ◽  
Lusiana Setiawati
Keyword(s):  
Erectile Dysfunction ◽  
Benign Prostatic Hyperplasia ◽  
Clinical Signs ◽  
Sampling Technique ◽  
Descriptive Study ◽  
Prostatic Hyperplasia ◽  
Cross Sectional ◽  
Purposive Sampling ◽  
Post Surgery ◽  
Cross Sectional Design

Abstract: Erectile dysfunction (ED) is an inability to achieve an erection sufficient for intercourse with his partner which causes dissatisfaction for both of them. The etiology of ED is classified as psychogenic, organic, drug abuse, and also by post-surgery. Benign prostatic hyperplasia (BPH) is a disease caused by aging. BPH clinical signs usually appear in more than 50% of men aged ≥50 years. This was a survey-descriptive study with a cross sectional design. Samples were obtained by using purposive sampling technique. Respondents were patients at Efrata Adventist Clinic in Manado. The instrument in this study was modified IIEF-5 questionnaire. The results showed that based on the duration of BPH, respondents who suffered from BPH >3 years were as many as 75.0% and <1 year were 7.1%. Based on the ages, respondents of 61-70 years were 46.5 and of 41-50 years were 7.1%. The erectile dysfunction of respondents was classified as moderate 42.9%, mild-moderate 32.1%, severe 17.9%, and mild 7.1%. Conclusion: Most of the erectile dysfunction with BPH >3 years was classified as moderate.Keywords: erectile dysfunction, BPH Abstrak: Disfungsi ereksi (DE) yaitu suatu ketidakmampuan untuk mencapai ereksi yang cukup untuk melakukan senggama bersama pasangannya sehingga menimbulkan ketidakpuasan diantara keduanya. Etiologi DE diklasifikasikan menjadi psikogenik, organik, penyalahgunaan obat-obatan dan juga oleh pasca tindakan bedah. Benign prostatic hyperplasia (BPH) adalah penyakit yang disebabkan oleh penuaan. Tanda klinis BPH biasanya muncul pada lebih dari 50% laki-laki yang berusia 50 tahun ke atas. Jenis penelitian ialah survei deskriptif-observasional dengan desain potong lintang. Pengambilan sampel dilakukan dengan teknik purposive sampling pada seluruh pasien di Klinik Advent Efrata Tikala Manado. Variabel penelitian ialah pasien BPH di Klinik Advent Tikala Manado. Instrumen penelitian menggunakan kuesioner IIEF-5 yang telah dimodifikasi. Hasil penelitian mendapatkan berdasarkan lama menderita BPH, responden yang menderita BPH >3 tahun sebesar 75,0%; 1-2 tahun sebesar 17,9%; dan <1 tahun sebesar 7,1%. Berdasarkan usia responden berusia 61-70 tahun sebesar 46,5% dan 41-50 tahun sebesar 7,1%. DE pada BPH paling banyak termasuk klasifikasi sedang (42,9%), diikuti ringan-sedang (32,1%), berat (17,9%) dan ringan (7,1%). Simpulan: Sebagian besar pasien DE dengan BPH >3 tahun termasuk dalam klasifikasi sedang. Kata kunci: disfungsi ereksi, BPH

Sign in / Sign up

Export Citation Format

Share Document