-
1.
A fusion decision system to identify and grade malnutrition in cancer patients: Machine learning reveals feasible workflow from representative real-world data.
Yin, L, Song, C, Cui, J, Lin, X, Li, N, Fan, Y, Zhang, L, Liu, J, Chong, F, Wang, C, et al
Clinical nutrition (Edinburgh, Scotland). 2021;(8):4958-4970
Abstract
BACKGROUND AND AIMS Most nutritional assessment tools are based on pre-defined questionnaires or consensus guidelines. However, it has been postulated that population data can be used directly to develop a solution for assessing malnutrition. This study established a machine learning (ML)-based, individualized decision system to identify and grade malnutrition using large-scale data from cancer patients. METHODS This was an observational, nationwide, multicenter cohort study that included 14134 cancer patients from five institutions in four different geographic regions of China. Multi-stage K-means clustering was performed to isolate and grade malnutrition based on 17 core nutritional features. The effectiveness of the identified clusters for reflecting clinical characteristics, nutritional status and patient outcomes was comprehensively evaluated. The study population was randomly split for model derivation and validation. Multiple ML algorithms were developed, validated and compared to screen for optimal models to implement the cluster prediction. RESULTS A well-nourished cluster (n = 8193, 58.0%) and a malnourished cluster with three phenotype-specific severity levels (mild = 2195, 15.5%; moderate = 2491, 17.6%; severe = 1255, 8.9%) were identified. The clusters showed moderate agreement with the Patient-Generated Subjective Global Assessment and the Global Leadership Initiative on Malnutrition criteria. The severity of malnutrition was negatively associated with the nutritional status, physical status, quality of life, and short-term outcomes, and was monotonically correlated with reduced overall survival. A multinomial logistic regression was found to be the optimal ML algorithm, and models built based on this algorithm showed almost perfect performance to predict the clusters in the validation data. CONCLUSIONS This study developed a fusion decision system that can be used to facilitate the identification and severity grading of malnutrition in patients with cancer. Moreover, the study workflow is flexible, and might provide a generalizable solution for the artificial intelligence-based assessment of malnutrition in a wider variety of scenarios.
-
2.
Combining a convolutional neural network with autoencoders to predict the survival chance of COVID-19 patients.
Khozeimeh, F, Sharifrazi, D, Izadi, NH, Joloudari, JH, Shoeibi, A, Alizadehsani, R, Gorriz, JM, Hussain, S, Sani, ZA, Moosaei, H, et al
Scientific reports. 2021;(1):15343
Abstract
COVID-19 has caused many deaths worldwide. The automation of the diagnosis of this virus is highly desired. Convolutional neural networks (CNNs) have shown outstanding classification performance on image datasets. To date, it appears that COVID computer-aided diagnosis systems based on CNNs and clinical information have not yet been analysed or explored. We propose a novel method, named the CNN-AE, to predict the survival chance of COVID-19 patients using a CNN trained with clinical information. Notably, the required resources to prepare CT images are expensive and limited compared to those required to collect clinical data, such as blood pressure, liver disease, etc. We evaluated our method using a publicly available clinical dataset that we collected. The dataset properties were carefully analysed to extract important features and compute the correlations of features. A data augmentation procedure based on autoencoders (AEs) was proposed to balance the dataset. The experimental results revealed that the average accuracy of the CNN-AE (96.05%) was higher than that of the CNN (92.49%). To demonstrate the generality of our augmentation method, we trained some existing mortality risk prediction methods on our dataset (with and without data augmentation) and compared their performances. We also evaluated our method using another dataset for further generality verification. To show that clinical data can be used for COVID-19 survival chance prediction, the CNN-AE was compared with multiple pre-trained deep models that were tuned based on CT images.
-
3.
Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey.
Asiri, N, Hussain, M, Al Adel, F, Alzaidi, N
Artificial intelligence in medicine. 2019;:101701
Abstract
Diabetic retinopathy (DR) results in vision loss if not treated early. A computer-aided diagnosis (CAD) system based on retinal fundus images is an efficient and effective method for early DR diagnosis and assisting experts. A computer-aided diagnosis (CAD) system involves various stages like detection, segmentation and classification of lesions in fundus images. Many traditional machine-learning (ML) techniques based on hand-engineered features have been introduced. The recent emergence of deep learning (DL) and its decisive victory over traditional ML methods for various applications motivated the researchers to employ it for DR diagnosis, and many deep-learning-based methods have been introduced. In this paper, we review these methods, highlighting their pros and cons. In addition, we point out the challenges to be addressed in designing and learning about efficient, effective and robust deep-learning algorithms for various problems in DR diagnosis and draw attention to directions for future research.
-
4.
Artificial intelligence in diabetic retinopathy: A natural step to the future.
Padhy, SK, Takkar, B, Chawla, R, Kumar, A
Indian journal of ophthalmology. 2019;(7):1004-1009
-
-
Free full text
-
Abstract
Use of artificial intelligence in medicine in an evolving technology which holds promise for mass screening and perhaps may even help in establishing an accurate diagnosis. The ability of complex computing is to perform pattern recognition by creating complex relationships based on input data and then comparing it with performance standards is a big step. Diabetic retinopathy is an ever-increasing problem. Early screening and timely treatment of the same can reduce the burden of sight threatening retinopathy. Any tool which can aid in quick screening of this disorder and minimize requirement of trained human resource for the same would probably be a boon for patients and ophthalmologists. In this review we discuss the current status of use of artificial intelligence in diabetic retinopathy and few other common retinal disorders.
-
5.
Impact of a Computerized Antithrombotic Risk Assessment Tool on the Prescription of Thromboprophylaxis in Atrial Fibrillation: Hospital Setting.
Pandya, E, Masood, N, Wang, Y, Krass, I, Bajorek, B
Clinical and applied thrombosis/hemostasis : official journal of the International Academy of Clinical and Applied Thrombosis/Hemostasis. 2018;(1):85-92
Abstract
The computerized antithrombotic risk assessment tool (CARAT) is an online decision-support algorithm that facilitates a systematic review of a patient's stroke risk, bleeding risk, and pertinent medication safety considerations, to generate an individualized treatment recommendation. The CARAT was prospectively applied across 2 hospitals in the greater Sydney area. Its impact on antithrombotics utilization for thromboprophylaxis in patients with nonvalvular atrial fibrillation was evaluated. Factors influencing prescribers' treatment selection were identified. The CARAT recommended a change in baseline therapy for 51.8% of patients. Among anticoagulant-eligible patients (ie, where the risk of stroke outweighed the risk of bleeding) using "nil therapy" or antiplatelet therapy at baseline, the CARAT recommended an upgrade to warfarin in 60 (30.8%) patients. For those in whom the bleeding risk outweighed the stroke risk, the CARAT recommended a downgrade from warfarin to safer alternatives (eg, aspirin) in 37 (19%) patients. Among the "most eligible" (ie, high stroke risk, low bleeding risk, no contraindications; n = 75), the CARAT recommended warfarin for all cases. Discharge therapy observed a marginal increase in anticoagulation prescription in eligible patients (n = 116; 57.8% vs 64.7%, P = .35) compared to baseline. Predictors of warfarin use (vs antiplatelets) included congestive cardiac failure, diabetes mellitus, and polypharmacy. The CARAT was able to optimize the selection of therapy, increasing anticoagulant use among eligible patients. With the increasing complexity of decision-making, such tools may be useful adjuncts in therapy selection in atrial fibrillation. Future studies should explore the utility of such tools in selecting therapies from within an expanded treatment armamentarium comprising the non-vitamin K antagonist oral anticoagulants.
-
6.
Deep learning in ophthalmology: a review.
Grewal, PS, Oloumi, F, Rubin, U, Tennant, MTS
Canadian journal of ophthalmology. Journal canadien d'ophtalmologie. 2018;(4):309-313
Abstract
Deep learning is an emerging technology with numerous potential applications in Ophthalmology. Deep learning tools have been applied to different diagnostic modalities including digital photographs, optical coherence tomography, and visual fields. These tools have demonstrated utility in assessment of various disease processes including cataracts, glaucoma, age-related macular degeneration, and diabetic retinopathy. Deep learning techniques are evolving rapidly, and will become more integrated into ophthalmic care. This article reviews the current evidence for deep learning in ophthalmology, and discusses future applications, as well as potential drawbacks.
-
7.
Automated Screening for Diabetic Retinopathy - A Systematic Review.
Nørgaard, MF, Grauslund, J
Ophthalmic research. 2018;(1):9-17
Abstract
PURPOSE Worldwide ophthalmologists are challenged by the rapid rise in the prevalence of diabetes. Diabetic retinopathy (DR) is the most common complication in diabetes, and possible consequences range from mild visual impairment to blindness. Repetitive screening for DR is cost-effective, but it is also a costly and strenuous affair. Several studies have examined the application of automated image analysis to solve this problem. Large populations are needed to assess the efficacy of such programs, and a standardized and rigorous methodology is important to give an indication of system performance in actual clinical settings. METHODS In a systematic review, we aimed to identify studies with methodology and design that are similar or replicate actual screening scenarios. A total of 1,231 publications were identified through PubMed, Cochrane Library, and Embase searches. Three manual search strategies were carried out to identify publications missed in the primary search. Four levels of screening identified 7 studies applicable for inclusion. RESULTS Seven studies were included. The detection of DR had high sensitivities (87.0-95.2%) but lower specificities (49.6-68.8%). False-negative results were related to mild DR with a low risk of progression within 1 year. Several studies reported missed cases of diabetic macular edema. A meta-analysis was not conducted as studies were not suitable for direct comparison or statistical analysis. CONCLUSION The study demonstrates that despite limited specificity, automated retinal image analysis may potentially be valuable in different DR screening scenarios with a relatively high sensitivity and a substantial workload reduction.
-
8.
Systemic Effects of Optos versus Indirect Ophthalmoscopy for Retinopathy of Prematurity Screening.
Fung, THM, Abramson, J, Ojha, S, Holden, R
Ophthalmology. 2018;(11):1829-1832
-
9.
An end to end secure CBIR over encrypted medical database.
Bellafqira, R, Coatrieux, G, Bouslimi, D, Quellec, G
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. 2016;:2537-2540
Abstract
In this paper, we propose a new secure content based image retrieval (SCBIR) system adapted to the cloud framework. This solution allows a physician to retrieve images of similar content within an outsourced and encrypted image database, without decrypting them. Contrarily to actual CBIR approaches in the encrypted domain, the originality of the proposed scheme stands on the fact that the features extracted from the encrypted images are themselves encrypted. This is achieved by means of homomorphic encryption and two non-colluding servers, we however both consider as honest but curious. In that way an end to end secure CBIR process is ensured. Experimental results carried out on a diabetic retinopathy database encrypted with the Paillier cryptosystem indicate that our SCBIR achieves retrieval performance as good as if images were processed in their non-encrypted form.
-
10.
Acute and training effects of resistance exercise on heart rate variability.
Kingsley, JD, Figueroa, A
Clinical physiology and functional imaging. 2016;(3):179-87
Abstract
Heart rate variability (HRV) has been used as a non-invasive method to evaluate heart rate (HR) regulation by the parasympathetic and sympathetic divisions of the autonomic nervous system. In this review, we discuss the effect of resistance exercise both acutely and after training on HRV in healthy individuals and in those with diseases characterized by autonomic dysfunction, such as hypertension and fibromyalgia. HR recovery after exercise is influenced by parasympathetic reactivation and sympathetic recovery to resting levels. Therefore, examination of HRV in response to acute exercise yields valuable insight into autonomic cardiovascular modulation and possible underlying risk for disease. Acute resistance exercise has shown to decrease cardiac parasympathetic modulation more than aerobic exercise in young healthy adults suggesting an increased risk for cardiovascular dysfunction after resistance exercise. Resistance exercise training appears to have no effect on resting HRV in healthy young adults, while it may improve parasympathetic modulation in middle-aged adults with autonomic dysfunction. Acute resistance exercise appears to decrease parasympathetic activity regardless of age. This review examines the acute and chronic effects of resistance exercise on HRV in young and older adults.