A nomogram-based diabetic sensorimotor polyneuropathy severity prediction using Michigan neuropathy screening instrumentations

Haque, Faiazul; Reaz, Mamun Bin Ibne; Chowdhury, Muhammad E. H.; Ali, Sawal Hamid Md; Bakar, Ahmad Ashrif A; Rahman, Tawsifur; Kobashi, Syoji; Dhawale, Chitra A.; Bhuiyan, Mohammad Arif Sobhan

doi:10.1016/j.compbiomed.2021.104954

Cited by 8 publications

(4 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Health professionals are more enthusiastic about using their advantages of flexibility and self-learning capacity as an aiding system for reliable performance. Intelligent systems based on ML algorithms have been intensively investigated for various biomedical systems, focusing on disease detection and risk reduction [ 16 , 17 , 18 , 49 , 50 ]. Like other severe diseases, CKD has piqued the interest of researchers in creating ML-based diagnosis systems for CKD [ 3 , 13 , 18 , 20 , 21 , 22 ].…”

Section: Discussionmentioning

confidence: 99%

Performance Analysis of Conventional Machine Learning Algorithms for Identification of Chronic Kidney Disease in Type 1 Diabetes Mellitus Patients

et al. 2021

Self Cite

View full text Add to dashboard Cite

Chronic kidney disease (CKD) is one of the severe side effects of type 1 diabetes mellitus (T1DM). However, the detection and diagnosis of CKD are often delayed because of its asymptomatic nature. In addition, patients often tend to bypass the traditional urine protein (urinary albumin)-based CKD detection test. Even though disease detection using machine learning (ML) is a well-established field of study, it is rarely used to diagnose CKD in T1DM patients. This research aimed to employ and evaluate several ML algorithms to develop models to quickly predict CKD in patients with T1DM using easily available routine checkup data. This study analyzed 16 years of data of 1375 T1DM patients, obtained from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials directed by the National Institute of Diabetes, Digestive, and Kidney Diseases, USA. Three data imputation techniques (RF, KNN, and MICE) and the SMOTETomek resampling technique were used to preprocess the primary dataset. Ten ML algorithms including logistic regression (LR), k-nearest neighbor (KNN), Gaussian naïve Bayes (GNB), support vector machine (SVM), stochastic gradient descent (SGD), decision tree (DT), gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and light gradient-boosted machine (LightGBM) were applied to developed prediction models. Each model included 19 demographic, medical history, behavioral, and biochemical features, and every feature’s effect was ranked using three feature ranking techniques (XGB, RF, and Extra Tree). Lastly, each model’s ROC, sensitivity (recall), specificity, accuracy, precision, and F-1 score were estimated to find the best-performing model. The RF classifier model exhibited the best performance with 0.96 (±0.01) accuracy, 0.98 (±0.01) sensitivity, and 0.93 (±0.02) specificity. LightGBM performed second best and was quite close to RF with 0.95 (±0.06) accuracy. In addition to these two models, KNN, SVM, DT, GB, and XGB models also achieved more than 90% accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Performance Analysis of Conventional Machine Learning Algorithms for Identification of Chronic Kidney Disease in Type 1 Diabetes Mellitus Patients

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The application of machine learning (ML) in medicine has extended to predicting clinical outcomes or classifying pertinent features in certain diseases. 11 12 In food allergies, studies have utilized ML to predict outcomes of milk, egg, peanut allergies held for diagnostic purposes. 13 14 ML enables identifying and selecting key variables from intricate datasets, a process sometimes too complex for traditional statistical methods.…”

Section: Introductionmentioning

confidence: 99%

Predicting the Outcome of Pediatric Oral Food Challenges for Determining Tolerance Development

Kim,

Jeong,

Park

et al. 2024

Allergy Asthma Immunol Res

View full text Add to dashboard Cite

Purpose Despite the risk of anaphylaxis, oral food challenges (OFCs) are performed clinically for various indications, particularly to confirm tolerance development. This study aimed to assess OFCs by relevant indications and build an outcome prediction model to help determine when to perform OFCs in children who are likely to have developed immune tolerance. Methods In total, 432 pediatric OFCs were retrospectively analyzed according to indications. Clinical characteristics, serum total immunoglobulin (Ig) E, blood eosinophils, and specific IgE and IgG4 levels for food allergens were noted and compared. Machine learning was utilized to select the most important variables in determining the passage of the OFCs, and prediction models were constructed using the selected variables. Results OFCs were most commonly performed to confirm tolerance development (number, %; 267, 61.8%). The most common food allergens tested were egg (191, 44.2%) and milk (135, 31.3%). Children who passed the egg challenges for confirming tolerance acquisition had significantly lower egg white-specific IgE level ( P = 0.008). Similarly, those who passed milk challenges had significantly lower cow’s milk-specific IgE ( P = 0.002) and casein-specific IgE levels ( P = 0.005). We developed a nomogram to predict the outcome of OFCs to determine the tolerance acquisition with the selected variables; lower food-specific IgE, higher total IgE, and younger age indicated a higher probability of passage. The area under the curve (95% confidence interval) was 0.623 (0.503–0.743) for egg and 0.734 (0.628–0.840) for milk. Conclusions Serum total IgE and food-specific IgE combined with age showed trends toward passing OFCs for confirming tolerance development. The constructed model may be used by clinicians as a practical guide for minimizing the risks of OFCs and a timely reintroduction for children with food allergies.

show abstract

“…The management of diabetic peripheral neuropathy encompasses targeted treatments for neurological symptoms and strategies to prevent DPN's progression and address foot complications [ 4 ]. However, the onset of DPN is insidious, and up to fifty percent of patients have no typical conscious symptoms, necessitating that clinicians and patients pay greater attention to early screening for DPN to provide timely and effective diagnosis and treatment [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Predictive value of TCM clinical index for diabetic peripheral neuropathy among the type 2 diabetes mellitus population: A new observation and insight

Tian

Fan

Sun

et al. 2023

Heliyon

View full text Add to dashboard Cite

A nomogram-based diabetic sensorimotor polyneuropathy severity prediction using Michigan neuropathy screening instrumentations

Cited by 8 publications

References 68 publications

Performance Analysis of Conventional Machine Learning Algorithms for Identification of Chronic Kidney Disease in Type 1 Diabetes Mellitus Patients

Performance Analysis of Conventional Machine Learning Algorithms for Identification of Chronic Kidney Disease in Type 1 Diabetes Mellitus Patients

Predicting the Outcome of Pediatric Oral Food Challenges for Determining Tolerance Development

Predictive value of TCM clinical index for diabetic peripheral neuropathy among the type 2 diabetes mellitus population: A new observation and insight

Contact Info

Product

Resources

About