| 1. |
- Javeed, Ashir, 1989-, et al.
(författare)
-
Predictive Power of XGBoost_BiLSTM Model : A Machine-Learning Approach for Accurate Sleep Apnea Detection Using Electronic Health Data
- 2023
-
Ingår i: International Journal of Computational Intelligence Systems. - : Springer Nature. - 1875-6891 .- 1875-6883. ; 16:1
-
Tidskriftsartikel (refereegranskat)abstract
- Sleep apnea is a common disorder that can cause pauses in breathing and can last from a few seconds to several minutes, as well as shallow breathing or complete cessation of breathing. Obstructive sleep apnea is strongly associated with the risk of developing several heart diseases, including coronary heart disease, heart attack, heart failure, and stroke. In addition, obstructive sleep apnea increases the risk of developing irregular heartbeats (arrhythmias), which can lead to low blood pressure. To prevent these conditions, this study presents a novel machine-learning (ML) model for predicting sleep apnea based on electronic health data that provides accurate predictions and helps in identifying the risk factors that contribute to the development of sleep apnea. The dataset used in the study includes 75 features and 10,765 samples from the Swedish National Study on Aging and Care (SNAC). The proposed model is based on two modules: the XGBoost module assesses the most important features from feature space, while the Bidirectional Long Short-Term Memory Networks (BiLSTM) module classifies the probability of sleep apnea. Using a cross-validation scheme, the proposed XGBoost_BiLSTM algorithm achieves an accuracy of 97% while using only the six most significant features from the dataset. The model’s performance is also compared with conventional long-short-term memory networks (LSTM) and other state-of-the-art ML models. The results of the study suggest that the proposed model improved the diagnosis and treatment of sleep apnea by identifying the risk factors.
|
|
| 2. |
- Javeed, Ashir, 1989-, et al.
(författare)
-
Decision Support System for Predicting Mortality in Cardiac Patients Based on Machine Learning
- 2023
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 13:8
-
Tidskriftsartikel (refereegranskat)abstract
- Researchers have proposed several automated diagnostic systems based on machine learning and data mining techniques to predict heart failure. However, researchers have not paid close attention to predicting cardiac patient mortality. We developed a clinical decision support system for predicting mortality in cardiac patients to address this problem. The dataset collected for the experimental purposes of the proposed model consisted of 55 features with a total of 368 samples. We found that the classes in the dataset were highly imbalanced. To avoid the problem of bias in the machine learning model, we used the synthetic minority oversampling technique (SMOTE). After balancing the classes in the dataset, the newly proposed system employed a (Formula presented.) statistical model to rank the features from the dataset. The highest-ranked features were fed into an optimized random forest (RF) model for classification. The hyperparameters of the RF classifier were optimized using a grid search algorithm. The performance of the newly proposed model ((Formula presented.) _RF) was validated using several evaluation measures, including accuracy, sensitivity, specificity, F1 score, and a receiver operating characteristic (ROC) curve. With only 10 features from the dataset, the proposed model (Formula presented.) _RF achieved the highest accuracy of 94.59%. The proposed model (Formula presented.) _RF improved the performance of the standard RF model by 5.5%. Moreover, the proposed model (Formula presented.) _RF was compared with other state-of-the-art machine learning models. The experimental results show that the newly proposed decision support system outperforms the other machine learning systems using the same feature selection module ((Formula presented.)).
|
|
| 3. |
- Lindberg, Terese, et al.
(författare)
-
Prevalence and Incidence of Atrial Fibrillation and Other Arrhythmias in the General Older Population : Findings From the Swedish National Study on Aging and Care
- 2019
-
Ingår i: Gerontology and geriatric medicine. - : SAGE PUBLICATIONS INC. - 2333-7214. ; 5
-
Tidskriftsartikel (refereegranskat)abstract
- Aim: To study the prevalence and cumulative incidence of arrhythmias in the general population of adults aged 60 and older over a 6-year period. Study Design and Setting: Data were taken from the Swedish National Study on Aging and Care (SNAC), a national, longitudinal, multidisciplinary study of the general elderly population (defined as 60 years of age or older). A 12-lead resting electrocardiography (ECG) was performed at baseline and 6-year follow-up. Results: The baseline prevalence of atrial fibrillation (AF) was 4.9% (95% confidence interval [CI] = [4.5%, 5.5%]), and other arrhythmias including ventricular premature complexes (VPCs), supraventricular tachycardia (SVT), and supraventricular extrasystole (SVES) were seen in 8.4% (7.7%, 9.0%) of the population. A first- or second-degree atrioventricular (AV) block was found in 7.1% of the population (95% CI = [6.5%, 7.7%]), and there were no significant differences between men and women in baseline arrhythmia prevalence. The 6-year cumulative incidence of AF was 4.1% (95% CI = [3.5%, 4.9%]), or 6.9/1,000 person-years (py; 95% CI = [5.7, 8.0]). The incidence of AF, other arrhythmias, AV block, and pacemaker-induced rhythm was significantly higher in men in all cohorts except for the oldest. Conclusion: Our data highlight the prevalence and incidence of arrhythmias, which rapidly increase with advancing age in the general population.
|
|
| 4. |
- Lindberg, Catharina, et al.
(författare)
-
The meaning of surviving three years after a heart transplant : a transition from uncertainty to acceptance through adaptation
- 2020
-
Ingår i: International Journal of Environmental Research and Public Health. - : MDPI. - 1661-7827 .- 1660-4601. ; 17:15
-
Tidskriftsartikel (refereegranskat)abstract
- The rationale was to longitudinally follow-up interviews performed with heart recipients at their one-year examination in order to deepen the understanding of the meaning of surviving a heart transplant. The aim was to explore the meaning of surviving three years after a heart transplant compared to one year and to identify what constitutes the change process. A phenomenological–hermeneutic method was used. This multicenter study was carried out at the two hospitals in Sweden where heart transplants are performed. A total of 13 heart recipients who survived three years after a heart transplant were invited to participate in this three-year follow-up study and 12 accepted, 3 women and 9 men, with a mean age of 51.25 years. The naïve understanding revealed that the heart recipients strongly accepted their life situation and that time had enabled this acceptance of limitations through adaptation. The thematic structural analyses cover six themes illustrating the meaning of acceptance and adaptation, i.e., accepting life as it is, adapting to post-transplant limitations, adapting to a changed body, social adaptation, showing gratitude and trusting oneself and others. In conclusion, achieving acceptance and a solid sense of self-efficacy after heart transplantation is a time-consuming process that involves courage to face and accept the reality and adapt in every life dimension. © 2020 by the authors. Licensee MDPI, Basel, Switzerland.
|
|
| 5. |
- Lindberg, Terese, et al.
(författare)
-
Older individuals’ need for knowledge and follow-up about their chronic atrial fibrillation, lifelong medical treatment and medical controls
- 2017
-
Ingår i: Scandinavian Journal of Caring Sciences. - : Wiley. - 0283-9318 .- 1471-6712. ; 31:4, s. 1022-1030
-
Tidskriftsartikel (refereegranskat)abstract
- Older individuals with chronic atrial fibrillation (AF) often experience physical symptoms and feel psychologically unwell. In addition, these persons are prescribed lifelong medical treatment that requires regular monitoring. Through 11 individual interviews, this interpretive description study aimed to explore and describe lifelong medical treatment and the need for medical controls as experienced from the perspective of older individuals living with chronic AF. The interviews were performed during 2014–2015; furthermore, they were recorded, transcribed verbatim and analysed for thematic patterns using thematic analysis inspired by Braun and Clarke. Ethical standards were followed throughout the study. The findings revealed one main theme: ‘ambivalence in the need of knowledge’ showing that lifelong medical treatment and the need for medical controls, in general, meant experiencing feelings of ‘it doesn't matter, but it does matter’ and ‘being in the hands of the healthcare system’. The older persons lacked knowledge about their condition, which generated poor insight into their medical treatment and this in turn affected their daily life. They had thoughts and questions about their medication, but did not have an opportunity to ask the questions because of lack of follow-up from the healthcare system. The findings underscore the negative impact chronic AF has on older people's life and emphasises the need for follow-up and providing information from health care to these individuals.
|
|
| 6. |
- Lindberg, Terese, et al.
(författare)
-
Prevalence of unknown and untreated arrhythmias in an older outpatient population screened by wireless long-term recording ECG
- 2016
-
Ingår i: Clinical Interventions in Aging. - 1176-9092 .- 1178-1998. ; 11, s. 1083-1090
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: With longer life expectancies, the prevalence of arrhythmias is increasing; thus, there is a need for new methods to screen the older outpatient population. This population-based study describes the prevalence of arrhythmias in 200 outpatients aged ≥66 years. We also investigated the feasibility of wireless long-term recording (LTR) using the ECG-BodyKom®. Methods: Two hundred elderly persons aged 66–93 years were recruited from the Swedish National Study on Aging and Care in 2010–2013, and data were collected via wireless LTR ECG-BodyKom. Results: Screening with the LTR ECG revealed that persistent atrial fibrillation (AF) occurred in 10% of the outpatient population aged ≥66 years. Paroxysmal AF occurred in 5.5% of the population, with no difference between younger (60–80 years) and older (≥80 years) elderly participants. Furthermore, all patients with paroxysmal AF had a CHA2DS2VASc score of ≥2 and were therefore potential candidates for follow-up and medical examination. LTR ECG-BodyKom can be considered a feasible method to screen for arrhythmias in older outpatient populations. This simple method requires little of the user, and there was high satisfaction with the equipment and a good overall experience wearing it. Conclusion: The increasing occurrence of arrhythmias in the older population, as well as the high number of untreated cases of arrhythmias such as persistent AF and paroxysmal AF, poses a challenge for health care. Therefore, it is essential to develop effective strategies for their prevention and treatment.
|
|
| 7. |
- Olsson, Anki, et al.
(författare)
-
Better platelet function, less fibrinolysis and less hemolysis in re-transfused residual pump blood with the Ringer’s chase technique : a randomized pilot study
- 2018
-
Ingår i: Perfusion. - : Sage Publications. - 0267-6591 .- 1477-111X. ; 33:3, s. 185-193
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: Residual pump blood from the cardiopulmonary bypass (CPB) circuit is often collected into an infusion bag (IB) and re-transfused. An alternative is to chase the residual blood into the circulation through the arterial cannula with Ringer’s acetate. Our aim was to assess possible differences in hemostatic blood quality between these two techniques.Methods: Forty adult patients undergoing elective coronary artery bypass graft surgery with CPB were randomized to receive the residual pump blood by either an IB or through the Ringer’s chase (RC) technique. Platelet activation and function (impedance aggregometry), coagulation and hemolysis variables were assessed in the re-transfused blood and in the patients before, during and after surgery. Results are presented as median (25-75 quartiles).Results: Total hemoglobin and platelet levels in the re-transfused blood were comparable with the two methods, as were soluble platelet activation markers P-selectin and soluble glycoprotein VI (GPVI). Platelet aggregation (U) in the IB blood was significantly lower compared to the RC blood, with the agonists adenosine diphosphate (ADP) 24 (10-32) vs 46 (33-65), p<0.01, thrombin receptor activating peptide (TRAP) 50 (29-73) vs 69 (51-92), p=0.04 and collagen 24 (17-28) vs 34 (26-59), p<0.01. The IB blood had higher amounts of free hemoglobin (mg/L) (1086 (891-1717) vs 591(517-646), p<0.01) and D-dimer 0.60 (0.33-0.98) vs 0.3 (0.3-0.48), p<0.01. Other coagulation variables showed no difference between the groups. Conclusions: The handling of blood after CPB increases hemolysis, impairs platelet function and activates coagulation and fibrinolysis. The RC technique preserved the blood better than the commonly used IB technique.
|
|
| 8. |
- Javeed, Ashir, 1989-, et al.
(författare)
-
An Intelligent Learning System for Unbiased Prediction of Dementia Based on Autoencoder and Adaboost Ensemble Learning
- 2022
-
Ingår i: Life. - : MDPI. - 2075-1729. ; 12:7, s. 1-18
-
Tidskriftsartikel (refereegranskat)abstract
- Dementia is a neurological condition that primarily affects older adults and there is stillno cure or therapy available to cure it. The symptoms of dementia can appear as early as 10 yearsbefore the beginning of actual diagnosed dementia. Hence, machine learning (ML) researchershave presented several methods for early detection of dementia based on symptoms. However,these techniques suffer from two major flaws. The first issue is the bias of ML models caused byimbalanced classes in the dataset. Past research did not address this issue well and did not takepreventative precautions. Different ML models were developed to illustrate this bias. To alleviate theproblem of bias, we deployed a synthetic minority oversampling technique (SMOTE) to balance thetraining process of the proposed ML model. The second issue is the poor classification accuracy ofML models, which leads to a limited clinical significance. To improve dementia prediction accuracy,we proposed an intelligent learning system that is a hybrid of an autoencoder and adaptive boostmodel. The autoencoder is used to extract relevant features from the feature space and the Adaboostmodel is deployed for the classification of dementia by using an extracted subset of features. Thehyperparameters of the Adaboost model are fine-tuned using a grid search algorithm. Experimentalfindings reveal that the suggested learning system outperforms eleven similar systems which wereproposed in the literature. Furthermore, it was also observed that the proposed learning systemimproves the strength of the conventional Adaboost model by 9.8% and reduces its time complexity.Lastly, the proposed learning system achieved classification accuracy of 90.23%, sensitivity of 98.00%and specificity of 96.65%.
|
|
| 9. |
- Widen, Cecilia, et al.
(författare)
-
Systemic inflammatory impact of periodontitis on acute coronary syndrome
- 2016
-
Ingår i: Journal of Clinical Periodontology. - : Wiley. - 0303-6979 .- 1600-051X. ; 43:9, s. 713-719
-
Tidskriftsartikel (refereegranskat)abstract
- AimA causative relationship between acute coronary syndrome (ACS) and periodontitis has yet to be defined. The aim of this study was to assess differences in levels of serum cytokines between individuals with or without ACS or periodontal comorbidity. Material and MethodsIn a case-control study, individuals with ACS (78 individuals, 10.3% females) and matching healthy controls (78 individuals, 28.2% females) were included. Medical and dental examinations were performed to diagnose ACS and periodontitis. Serum levels of cytokines were assessed, using Luminex technology. ResultsA diagnosis of periodontitis in the ACS and control group was diagnosed in 52.6% and 12.8% of the individuals, respectively. The unadjusted odds-ratio that individuals with ACS also had periodontitis was 7.5 (95% CI: 3.4, 16.8, p<0.001). Independent of periodontal conditions, individuals with ACS had significantly higher serum levels of IL8 (mean: 44.3 and 40.0pg/ml) and vascular endothelial growth factor (VEGF) (mean: 82.3 and 55.3pg/ml) than control individuals. A diagnosis of periodontitis made no difference in serum cytokine expressions. ConclusionElevated serum levels of VEGF were associated with ACS. Serum cytokine expression in individuals with ACS is unrelated to periodontal conditions.
|
|
| 10. |
- Bengtsson, Viveca Wallin, et al.
(författare)
-
Periodontitis related to cardiovascular events and mortality : a long-time longitudinal study
- 2021
-
Ingår i: Clinical Oral Investigations. - : Springer Science and Business Media Deutschland GmbH. - 1432-6981 .- 1436-3771. ; 25:6, s. 4085-4095
-
Tidskriftsartikel (refereegranskat)abstract
- Objective: The present study assessed if individuals ≥ 60 years of age with periodontitis are more likely to develop stroke or ischemic heart diseases, or at a higher risk of death for 17 years. Material and methods: At baseline individuals ≥ 60 received a dental examination including a panoramic radiograph. Periodontitis was defined as having ≥ 30% sites with ≥ 5-mm distance from the cementoenamel junction to the marginal bone level. Medical records were annually reviewed from 2001 to 2018. Findings from the medical records identifying an ICD-10 code of stroke and ischemic heart diseases or death were registered. Results: Associations between periodontitis and incidence of ischemic heart disease were found in this 17-year follow-up study in all individuals 60–93 years (HR: 1.5, CI: 1.1–2.1, p = 0.017), in women (HR: 2.1, CI: 1.3–3.4, p = 0.002), and in individuals 78–96 years (HR: 1.7, CI: 1.0–2.6, p = 0.033). Periodontitis was associated with mortality in all individuals (HR: 1.4, CI: 1.2–1.8, p = 0.002), specifically in men (HR: 1.5, CI: 1.1–1.9, p = 0.006) or in ages 60–72 years (HR: 2.2, CI: 1.5–3.2, p = 0.000). Periodontitis was more prevalent among men (OR: 1.8, CI: 1.3–2.4, p = 0.000). Conclusions: Individuals with periodontitis have an increased risk for future events of ischemic heart diseases and death. Clinical relevance: Improving periodontal health in older individuals may reduce overall mortality and ischemic heart diseases. Both dental and medical professionals should be aware of the associations and ultimately cooperate. © 2021, The Author(s).
|
|
