An experimental machine learning study investigating the decision-making process of students and qualified radiographers when interpreting radiographic images

Clinical, genomic, and proteomic perspectives in the analysis of comorbid conditions in type 2 diabetes mellitus: a retrospective study

AIM

Type-2 Diabetes Mellitus (T2DM) affects millions globally, with escalating rates. It often leads to undiagnosed complications and commonly coexists with other health conditions. This study investigates two types of prevalent comorbidities related to T2DM-the circulatory system (DCM1) and digestive system diseases (DCM2)-using clinical, genomic and proteomic datasets. The aim is to identify new biomarkers by applying existing machine learning (ML) based techniques for early detection, prognosis and diagnosis of these comorbidities.

METHODS

Here, we report a cross-sectional retrospective analysis from a T2DM dataset of T2DM associated concordant comorbidities (diseases with shared pathophysiology and management) from the Diastrat cohort (a T2DM cohort) recruited at the Northern Ireland Centre for Stratified Medicine (NICSM), in Northern Ireland.

RESULTS

In the clinical data analysis, we identified that lipidemia was shown to negatively correlate with depression in the DCM1 group while positively correlate with depression in the DCM2 group. In genomic analysis, we identified statistically significant variants rs9844730 in procollagen-lysine (PLOD2), rs73590361 in beta-1,4-N-acetyl- galactosaminyl-transferase (B4GALNT3) and rs964680 in A kinase (PRKA) anchor protein 14 (AKAP14) which appear to differentiate DCM1 and DCM2 groups. In proteomic analysis, we identified 4 statistically significant proteins: natriuretic peptides B (BNP), pro-adrenomedullin (ADM), natriuretic peptides B (NT-proBNP) and discoidin (DCBLD2) that can differentiate DCM1 and DCM2 groups and have built robust ML model using clinical, genomic, and proteomic markers (0.83 receiver operative characteristics curve area, 84% positive predictive value and 83% negative predictive value and a classification accuracy of 83%) for prediction of DCM1 and DCM2 groups.

CONCLUSION

Our study successfully identifies novel clinical, genomic, and proteomic biomarkers that differentiate between circulatory and digestive system comorbidities in Type-2 Diabetes Mellitus patients. The machine learning model we developed demonstrates strong predictive capabilities, providing a promising tool for the early detection, prognosis, and diagnosis of these T2DM-associated comorbidities. These findings have the potential to enhance personalized management strategies for patients with T2DM, ultimately improving clinical outcomes. Further research is needed to validate these biomarkers and integrate them into clinical practice.

Enhancing Medical Training Through Learning From Mistakes by Interacting With an Ill-Trained Reinforcement Learning Agent

This study presents a 3D medical simulation that employs reinforcement learning (RL) and interactive reinforcement learning (IRL) to teach and assess the procedure of donning and doffing personal protective equipment (PPE). The simulation is motivated by the need for effective, safe, and remote training techniques in medicine, particularly in light of the COVID-19 pandemic. The simulation has two modes: a tutorial mode and an assessment mode. In the tutorial mode, a computer-based, ill-trained RL agent utilizes RL to learn the correct sequence of donning the PPE by trial and error. This allows students to experience many outlier cases they might not encounter in an in-class educational model. In the assessment mode, an IRL-based method is used to evaluate how effective the participant is at correcting the mistakes performed by the RL agent. Each time the RL agent interacts with the environment and performs an action, the participants provide positive or negative feedback regarding the action taken. Following the assessment, participants receive a score based on the accuracy of their feedback and the time taken for the RL agent to learn the correct sequence. An experiment was conducted using two groups, each consisting of 10 participants. The first group received RL-assisted training for donning PPE, followed by an IRL-based assessment. Meanwhile, the second group observed a video featuring the RL agent demonstrating only the correct donning order without outlier cases, replicating traditional training, before undergoing the same assessment as the first group. Results showed that RL-assisted training with many outlier cases was more effective than traditional training with only regular cases. Moreover, combining RL with IRL significantly enhanced the participants' performance. Notably, 90% of the participants finished the assessment with perfect scores within three iterations. In contrast, only 10% of those who did not engage in RL-assisted training finished the assessment with a perfect score, highlighting the substantial impact of RL and IRL integration on participants' overall achievement.

Exploring metformin monotherapy response in Type-2 diabetes: Computational insights through clinical, genomic, and proteomic markers using machine learning algorithms

BACKGROUND

In 2016, the UK had 4.5 million people with diabetes, predominantly Type-2 Diabetes Mellitus (T2DM). The NHS allocates £10 billion (9% of its budget) to manage diabetes. Metformin is the primary treatment for T2DM, but 35% of patients don't benefit from it, leading to complications. This study aims to delve into metformin's efficacy using clinical, genomic, and proteomic data to uncover new biomarkers and build a Machine Learning predictor for early metformin response detection.

METHODS

Here we report analysis from a T2DM dataset of individuals prescribed metformin monotherapy from the Diastrat cohort recruited at the Altnagelvin Area Hospital, Northern Ireland.

RESULTS

In the clinical data analysis, comparing responders (those achieving HbA1c ≤ 48 mmol/mol) to non-responders (with HbA1c > 48 mmol/mol), we identified that creatinine levels and bodyweight were more negatively correlated with response than non-response. In genomic analysis, we identified statistically significant (p-value <0.05) variants rs6551649 (LPHN3), rs6551654 (LPHN3), rs4495065 (LPHN3) and rs7940817 (TRPC6) which appear to differentiate the responders and non-responders. In proteomic analysis, we identified 15 statistically significant (p-value <0.05, q-value <0.05) proteomic markers that differentiate controls, responders, non-responders and treatment groups, out of which the most significant were HAOX1, CCL17 and PAI that had fold change ∼2. A machine learning model was build; the best model predicted non-responders with 83% classification accuracy.

CONCLUSION

Further testing in prospective validation cohorts is required to determine the clinical utility of the proposed model.