| 1. |
- Cao, Yang, Associate Professor, 1972-, et al.
(författare)
-
Using a Convolutional Neural Network to Predict Remission of Diabetes After Gastric Bypass Surgery : Machine Learning Study From the Scandinavian Obesity Surgery Register
- 2021
-
Ingår i: JMIR Medical Informatics. - : JMIR Publications. - 2291-9694. ; 9:8
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Prediction of diabetes remission is an important topic in the evaluation of patients with type 2 diabetes (T2D) before bariatric surgery. Several high-quality predictive indices are available, but artificial intelligence algorithms offer the potential for higher predictive capability.OBJECTIVE: This study aimed to construct and validate an artificial intelligence prediction model for diabetes remission after Roux-en-Y gastric bypass surgery.METHODS: Patients who underwent surgery from 2007 to 2017 were included in the study, with collection of individual data from the Scandinavian Obesity Surgery Registry (SOReg), the Swedish National Patients Register, the Swedish Prescribed Drugs Register, and Statistics Sweden. A 7-layer convolution neural network (CNN) model was developed using 80% (6446/8057) of patients randomly selected from SOReg and 20% (1611/8057) of patients for external testing. The predictive capability of the CNN model and currently used scores (DiaRem, Ad-DiaRem, DiaBetter, and individualized metabolic surgery) were compared.RESULTS: In total, 8057 patients with T2D were included in the study. At 2 years after surgery, 77.09% achieved pharmacological remission (n=6211), while 63.07% (4004/6348) achieved complete remission. The CNN model showed high accuracy for cessation of antidiabetic drugs and complete remission of T2D after gastric bypass surgery. The area under the receiver operating characteristic curve (AUC) for the CNN model for pharmacological remission was 0.85 (95% CI 0.83-0.86) during validation and 0.83 for the final test, which was 9%-12% better than the traditional predictive indices. The AUC for complete remission was 0.83 (95% CI 0.81-0.85) during validation and 0.82 for the final test, which was 9%-11% better than the traditional predictive indices.CONCLUSIONS: The CNN method had better predictive capability compared to traditional indices for diabetes remission. However, further validation is needed in other countries to evaluate its external generalizability.
|
|
| 2. |
- Cao, Yang, Associate Professor, 1972-, et al.
(författare)
-
A Comparative Study of Machine Learning Algorithms in Predicting Severe Complications after Bariatric Surgery
- 2019
-
Ingår i: Journal of Clinical Medicine. - : MDPI. - 2077-0383. ; 8:5
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Severe obesity is a global public health threat of growing proportions. Accurate models to predict severe postoperative complications could be of value in the preoperative assessment of potential candidates for bariatric surgery. So far, traditional statistical methods have failed to produce high accuracy. We aimed to find a useful machine learning (ML) algorithm to predict the risk for severe complication after bariatric surgery.Methods: We trained and compared 29 supervised ML algorithms using information from 37,811 patients that operated with a bariatric surgical procedure between 2010 and 2014 in Sweden. The algorithms were then tested on 6250 patients operated in 2015. We performed the synthetic minority oversampling technique tackling the issue that only 3% of patients experienced severe complications.Results: Most of the ML algorithms showed high accuracy (>90%) and specificity (>90%) in both the training and test data. However, none of the algorithms achieved an acceptable sensitivity in the test data. We also tried to tune the hyperparameters of the algorithms to maximize sensitivity, but did not yet identify one with a high enough sensitivity that can be used in clinical praxis in bariatric surgery. However, a minor, but perceptible, improvement in deep neural network (NN) ML was found.Conclusion: In predicting the severe postoperative complication among the bariatric surgery patients, ensemble algorithms outperform base algorithms. When compared to other ML algorithms, deep NN has the potential to improve the accuracy and it deserves further investigation. The oversampling technique should be considered in the context of imbalanced data where the number of the interested outcome is relatively small.
|
|
| 3. |
- Cao, Yang, Associate Professor, 1972-, et al.
(författare)
-
Deep Learning Neural Networks to Predict Serious Complications After Bariatric Surgery : Analysis of Scandinavian Obesity Surgery Registry Data
- 2020
-
Ingår i: JMIR Medical Informatics. - : JMIR Publications. - 2291-9694. ; 8:5
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Obesity is one of today's most visible public health problems worldwide. Although modern bariatric surgery is ostensibly considered safe, serious complications and mortality still occur in some patients.OBJECTIVE: This study aimed to explore whether serious postoperative complications of bariatric surgery recorded in a national quality registry can be predicted preoperatively using deep learning methods.METHODS: Patients who were registered in the Scandinavian Obesity Surgery Registry (SOReg) between 2010 and 2015 were included in this study. The patients who underwent a bariatric procedure between 2010 and 2014 were used as training data, and those who underwent a bariatric procedure in 2015 were used as test data. Postoperative complications were graded according to the Clavien-Dindo classification, and complications requiring intervention under general anesthesia or resulting in organ failure or death were considered serious. Three supervised deep learning neural networks were applied and compared in our study: multilayer perceptron (MLP), convolutional neural network (CNN), and recurrent neural network (RNN). The synthetic minority oversampling technique (SMOTE) was used to artificially augment the patients with serious complications. The performances of the neural networks were evaluated using accuracy, sensitivity, specificity, Matthews correlation coefficient, and area under the receiver operating characteristic curve.RESULTS: In total, 37,811 and 6250 patients were used as the training data and test data, with incidence rates of serious complication of 3.2% (1220/37,811) and 3.0% (188/6250), respectively. When trained using the SMOTE data, the MLP appeared to have a desirable performance, with an area under curve (AUC) of 0.84 (95% CI 0.83-0.85). However, its performance was low for the test data, with an AUC of 0.54 (95% CI 0.53-0.55). The performance of CNN was similar to that of MLP. It generated AUCs of 0.79 (95% CI 0.78-0.80) and 0.57 (95% CI 0.59-0.61) for the SMOTE data and test data, respectively. Compared with the MLP and CNN, the RNN showed worse performance, with AUCs of 0.65 (95% CI 0.64-0.66) and 0.55 (95% CI 0.53-0.57) for the SMOTE data and test data, respectively.CONCLUSIONS: MLP and CNN showed improved, but limited, ability for predicting the postoperative serious complications after bariatric surgery in the Scandinavian Obesity Surgery Registry data. However, the overfitting issue is still apparent and needs to be overcome by incorporating intra- and perioperative information.
|
|
| 4. |
- Dahlberg, Karuna, 1979-, et al.
(författare)
-
Incident self-harm after bariatric surgery : A nationwide registry-based matched cohort study
- 2023
-
Ingår i: Clinical Obesity. - : John Wiley & Sons. - 1758-8103 .- 1758-8111. ; 13:3
-
Tidskriftsartikel (refereegranskat)abstract
- The aims of this study were to evaluate the longitudinal risk of self-harm and the risk factors for self-harm after bariatric surgery in patients and control subjects without prior self-harm. This observational cohort study was based on prospectively registered data. Patients 18–70 years at time of surgery, body mass index (BMI) > 30 kg/m2, who underwent a primary Roux-en-Y gastric bypass (RYGB) procedure or a primary sleeve gastrectomy between 2007 and 2019 were considered for inclusion. All patients who met the inclusion criteria were matched 1:10 to the general population in Sweden (69 492 patients vs. 694 920 controls). After excluding patients and controls with previous self-harm, a self-harm event occurred in 1408 patients in the surgical group (incidence rate (IR) 3.54/1000 person-years, 95% confidence interval (CI) 3.36–3.73) versus in 3162 patients in the control group (IR 0.81/1000 person-years, 95% CI 0.78–0.84), with a hazard ratio (HR) of 4.38 (95% CI 4.11–4.66, p < .001). Median follow-up time was 6.1 years. Risk factors were younger age, lower BMI, cardiovascular, and chronic obstructive pulmonary disease, all aspects of psychiatric comorbidities (except neuropsychiatric disorder), lower socioeconomic status, RYGB, lower health-related quality of life, lower postoperative weight loss, and not attending postoperative follow-up visits. Self-harm is clearly higher after bariatric surgery than in the general population. A qualitative follow-up may be particularly important for patients at increased risk.
|
|
| 5. |
- Raoof, Mustafa, 1966-, et al.
(författare)
-
Improvements of health-related quality of life 5 years after gastric bypass. What is important besides weight loss? A study from Scandinavian Obesity Surgery Register
- 2020
-
Ingår i: Surgery for Obesity and Related Diseases. - : Elsevier. - 1550-7289 .- 1878-7533. ; 16:9, s. 1249-1257
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Obesity continues to increase in the world. It is strongly associated with morbidity, mortality, and decrease of health-related quality of life (HRQoL). Surgery is the most effective treatment for obesity, resulting in sustained weight loss and improvements of HRQoL. The aim of this study was to examine whether other factors, apart from weight loss, are associated with improvement in HRQoL scores between the preoperative visit and the 5-year follow-up.OBJECTIVES: To examine whether there are factors besides weight loss that affect the improvement of HRQoL from before to 5 years after gastric bypass surgery.SETTING: Large, nationwide, observational study with national quality and research registry.METHODS: Patients operated with a primary gastric bypass in Sweden between January 2008 and December 2012 were identified in the Scandinavian Obesity Surgery Register. Patients with HRQoL data available at both baseline and 5 years after surgery were included. Two HRQoL instruments, the RAND Short form-36 and the obesity-related problems scale, were used in the study.RESULTS: The study sample comprised 6998 patients (21% men). Differences in HRQoL change according to sex were minor. Younger patients showed greater improvements in physical health scales. In general linear regression model analyses, age and weight loss correlated significantly with improvement in HRQoL after 5 years. Patients treated medically for depression preoperatively (13%) experienced less improvement in HRQoL than patients without such treatment. Patients with postoperative complications (26%) had significantly less improvements in all aspects of HRQoL compared with those without any form of postoperative complication.CONCLUSION: The study confirmed the importance of weight loss for improvement in HRQoL after bariatric surgery. Preoperative medication for depression and suffering a complication during the 5-year follow-up period were associated with less improvement in HRQoL.
|
|
| 6. |
|
|
| 7. |
- Stenberg, Erik, 1979-, et al.
(författare)
-
Association between attention deficit hyperactivity disorder and outcomes after metabolic and bariatric surgery : a nationwide propensity-matched cohort study
- 2023
-
Ingår i: Surgery for Obesity and Related Diseases. - : Elsevier. - 1550-7289 .- 1878-7533. ; 19:2, s. 92-100
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: The risks and benefits of metabolic and bariatric surgery for patients with attention deficit hyperactivity disorder (ADHD) remain to be investigated.OBJECTIVE: The aim of this study was to assess short- and long-term outcomes after metabolic and bariatric surgery in patients with previous ADHD compared with matched control individuals.SETTING: Registry based.METHODS: This 2-staged matched-cohort study included all adults with a body mass index of ≥30 kg/m2 who underwent primary Roux-en-Y gastric bypass or sleeve gastrectomy from 2007 until 2017 registered in the Scandinavian Obesity Surgery Registry. Patients with prescribed medication for ADHD were matched with control individuals without ADHD with a follow-up of up to 11 years after surgery.RESULTS: Among 1431 patients with ADHD and 2862 control individuals (mean body mass index, 42 kg/m2; mean age, 35 years), no difference in weight loss or follow-up attendance over 2 years was seen. ADHD was associated with a higher risk for early postoperative complications (odds ratio [OR] = 1.31; 95% confidence interval [CI], 1.05-1.63), self-harm (hazards ratio [HR] = 1.39; 95% CI, 1.11-1.75), and substance abuse (HR = 1.34; 95% CI, 1.16-1.55), while associations with overall mortality (HR = 1.42; 95% CI, .99-2.03), major adverse cardiovascular and cerebrovascular events (HR = 1.93; 95% CI, .98-3.83), and effects on obesity-related diseases were uncertain. ADHD was associated with a lower health-related quality of life in all aspects before surgery. These differences increased for mental and obesity-related aspects but remained unchanged over time for physical aspects.CONCLUSIONS: Compared with patients without ADHD, patients treated pharmacologically for ADHD experience similar weight loss and remission of obesity-related diseases without an increased risk for serious complications but report a lower health-related quality of life and have an increased risk of substance abuse and self-harm. This further emphasizes the need for close follow-up care for this group of individuals.
|
|
| 8. |
- Stenberg, Erik, 1979-, et al.
(författare)
-
Association between metabolic surgery and cardiovascular outcome in patients with hypertension : A nationwide matched cohort study
- 2020
-
Ingår i: PLoS Medicine. - : Public Library of Science (PLoS). - 1549-1277 .- 1549-1676. ; 17:9
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Hypertension, together with obesity, is a leading cause of mortality and disability. Whilst metabolic surgery offers remission of several metabolic comorbidities, the effect for patients with hypertension remains controversial. The objective of the present study was to evaluate the effect of metabolic surgery on cardiovascular events and mortality on patients with morbid obesity (body mass index [BMI] ≥ 35 kg/m2) and hypertension.METHODS AND FINDINGS: We conducted a matched cohort study of 11,863 patients with morbid obesity and pharmacologically treated hypertension operated on with metabolic surgery and a matched non-operated-on control group of 26,199 subjects with hypertension (matched by age, sex, and area of residence) of varied matching ratios from 1:1 to 1:9, using data from the Scandinavian Obesity Surgery Register (SOReg), the Swedish National Patient Registers (NPR) for in-hospital and outpatient care, the Swedish Prescribed Drug Register, and Statistics Sweden. The main outcome was major adverse cardiovascular event (MACE), defined as first occurrence of acute coronary syndrome (ACS) event, cerebrovascular event, fatal cardiovascular event, or unattended sudden cardiac death. The mean age in the study group was 52.1 ± 7.46 years, with 65.8% being women (n = 7,810), and mean BMI was 41.9 ± 5.43 kg/m2. MACEs occurred in 379 operated-on patients (3.2%) and 1,125 subjects in the control group (4.5%). After adjustment for duration of hypertension, comorbidities, and education, a reduction in risk was seen in the metabolic surgery group (adjusted hazard ratio [HR] 0.73, 95% confidence intervals [CIs] 0.64-0.84, P < 0.001). The surgery group had lower risk for ACS events (adjusted HR 0.52, 95% CI 0.41-0.66, P < 0.001) and a tendency towards lower risk for cerebrovascular events (adjusted HR 0.81, 95% CI 0.63-1.01, P = 0.060) compared with controls. The main limitations with the study were the lack of information on BMI and history of smoking in the control group and the nonrandomised study design.CONCLUSION: Metabolic surgery on patients with morbid obesity and pharmacologically treated hypertension was associated with lower risk for MACEs and all-cause mortality compared with age- and sex-matched controls with hypertension from the general population.
|
|
| 9. |
- Stenberg, Erik, 1979-, et al.
(författare)
-
Factors determining chance of type 2 diabetes remission after Roux-en-Y gastric bypass surgery : a nationwide cohort study in 8057 Swedish patients
- 2021
-
Ingår i: BMJ Open Diabetes Research & Care. - : BMJ Publishing Group Ltd. - 2052-4897. ; 9:1
-
Tidskriftsartikel (refereegranskat)abstract
- INTRODUCTION: Bariatric and metabolic surgery is an effective treatment option for type 2 diabetes (T2D). Increased knowledge regarding factors associated with diabetes remission is essential in individual decision making and could guide postoperative care. Therefore, we aimed to explore factors known to affect the chance of achieving diabetes remission after bariatric and metabolic surgery and to further investigate the impact of socioeconomic factors.RESEARCH DESIGN AND METHODS: In this nationwide study, we assessed all patients with T2D who underwent Roux-en-Y gastric bypass (RYGB) surgery between 2007 and 2015 in the Scandinavian Obesity Surgery Registry. Remission was defined as absence of antidiabetic medication for T2D 2 years after surgery. Multivariable logistic regression was used to evaluate factors associated with diabetes remission, with missing data handled by multiple imputations.RESULTS: , mean hemoglobin A1c 59.0±17.33, and 61.7% (n=4970) were women. Two years after surgery, 6211 (77.1%) patients achieved T2D remission. Preoperative insulin treatment (OR 0.26, 95% CI 0.22 to 0.30), first-generation immigrant (OR 0.66, 95% CI 0.57 to 0.77), duration of T2D (OR 0.89, 95% CI 0.88 to 0.90), dyslipidemia (OR 0.71, 95% CI 0.62 to 0.81), age (OR 0.97, 95% CI 0.96 to 0.97), and high glycosylated hemoglobin A1c (HbA1c) (OR 0.99, 95% CI 0.98 to 0.99) were all associated with lower T2D remission rate. In contrast, residence in a medium-sized (OR 1.39, 95% CI 1.20 to 1.61) or small (OR 1.46, 95% CI 1.25 to 1.71) town and percentage of total weight loss (OR 1.04, 95% CI 1.03 to 1.04) were associated with higher remission rates.CONCLUSION: Among patients with T2D undergoing RYGB surgery, increasing age, HbA1c, and diabetes duration decreased the chance of reaching diabetes remission without cut-offs, while postoperative weight loss demonstrated a positive linear association. In addition, being a first-generation immigrant and living in a large city were socioeconomic factors having a negative association.
|
|
| 10. |
- Stenberg, Erik, 1979-, et al.
(författare)
-
Limited Effect of Beta-blockade on Postoperative Outcome After Laparoscopic Gastric Bypass Surgery
- 2020
-
Ingår i: Obesity Surgery. - : Springer Science+Business Media B.V.. - 0960-8923 .- 1708-0428. ; 30:1, s. 139-145
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: The benefit of beta-blockade on postoperative outcome remains controversial, though recent studies have suggested a role during major non-cardiac surgery. The benefit of beta-blockade during minimally invasive gastric bypass surgery remains unclear. The aim of the present study was to evaluate the possible association between preoperative beta-blocker therapy and postoperative outcome after laparoscopic gastric bypass surgery.METHODS: Patients operated with primary laparoscopic gastric bypass surgery in Sweden between 2007 and 2017 were identified through the Scandinavian Obesity Surgery Registry. The dataset was linked to the Swedish National Patient Registry, the Swedish Prescribed Drug Registry, and Statistics Sweden. The main outcome was serious postoperative complication within 30 days of surgery; with postoperative complication, 90-day and 1-year mortality, and weight loss at 2 years after surgery as secondary endpoints. The Poisson regression model was used to evaluate primary and secondary categorical outcomes. A general mixed model was performed to evaluate 2-year weight loss.RESULTS: In all, 50281 patients were included in the study. No difference was seen between patients on beta-blockade and the control group regarding postoperative complications (adjusted incidence rate ratio 1.04 (95%CI 0.93-1.15), p = 0.506), serious postoperative complication (adjusted IRR 1.06 95%CI 0.89-1.27), p = 0.515), 90-day mortality (adjusted IRR 0.71 (95%CI 0.24-2.10), p = 0.537), and 1-year mortality (adjusted IRR 1.26 (95%CI 0.67-2.36), p = 0.467). Weight loss 2 years after surgery was slightly greater in patients on beta-blockade (adjusted coefficient 0.53 (95%CI 0.19-0.87), p = 0.002).CONCLUSIONS: Beta-blockade has limited impact on postoperative outcome after laparoscopic gastric bypass surgery.
|
|
