An explainable machine learning-based clinical decision support system for prediction of gestational diabetes mellitus

Artificial intelligence model for tumoral clinical decision support systems

BACKGROUND AND OBJECTIVE

Comparative diagnostic in brain tumor evaluation makes possible to use the available information of a medical center to compare similar cases when a new patient is evaluated. By leveraging Artificial Intelligence models, the proposed system is able of retrieving the most similar cases of brain tumors for a given query. The primary objective is to enhance the diagnostic process by generating more accurate representations of medical images, with a particular focus on patient-specific normal features and pathologies. A key distinction from previous models lies in its ability to produce enriched image descriptors solely from binary information, eliminating the need for costly and difficult to obtain tumor segmentation.

METHODS

The proposed model uses Artificial Intelligence to detect patient features to recommend the most similar cases from a database. The system not only suggests similar cases but also balances the representation of healthy and abnormal features in its design. This not only encourages the generalization of its use but also aids clinicians in their decision-making processes. This generalization makes possible for future research in different medical diagnosis areas with almost not any change in the system.

RESULTS

We conducted a comparative analysis of our approach in relation to similar studies. The proposed architecture obtains a Dice coefficient of 0.474 in both tumoral and healthy regions of the patients, which outperforms previous literature. Our proposed model excels at extracting and combining anatomical and pathological features from brain Magnetic Resonances (MRs), achieving state-of-the-art results while relying on less expensive label information. This substantially reduces the overall cost of the training process. Our findings highlight the significant potential for improving the efficiency and accuracy of comparative diagnostics and the treatment of tumoral pathologies.

CONCLUSIONS

This paper provides substantial grounds for further exploration of the broader applicability and optimization of the proposed architecture to enhance clinical decision-making. The novel approach presented in this work marks a significant advancement in the field of medical diagnosis, particularly in the context of Artificial Intelligence-assisted image retrieval, and promises to reduce costs and improve the quality of patient care using Artificial Intelligence as a support tool instead of a black box system.

The role of machine learning algorithms in detection of gestational diabetes; a narrative review of current evidence

Gestational Diabetes Mellitus (GDM) poses significant health risks to mothers and infants. Early prediction and effective management are crucial to improving outcomes. Machine learning techniques have emerged as powerful tools for GDM prediction. This review compiles and analyses the available studies to highlight key findings and trends in the application of machine learning for GDM prediction. A comprehensive search of relevant studies published between 2000 and September 2023 was conducted. Fourteen studies were selected based on their focus on machine learning for GDM prediction. These studies were subjected to rigorous analysis to identify common themes and trends. The review revealed several key themes. Models capable of predicting GDM risk during the early stages of pregnancy were identified from the studies reviewed. Several studies underscored the necessity of tailoring predictive models to specific populations and demographic groups. These findings highlighted the limitations of uniform guidelines for diverse populations. Moreover, studies emphasised the value of integrating clinical data into GDM prediction models. This integration improved the treatment and care delivery for individuals diagnosed with GDM. While different machine learning models showed promise, selecting and weighing variables remains complex. The reviewed studies offer valuable insights into the complexities and potential solutions in GDM prediction using machine learning. The pursuit of accurate, early prediction models, the consideration of diverse populations, clinical data, and emerging data sources underscore the commitment of researchers to improve healthcare outcomes for pregnant individuals at risk of GDM.

Tongue image fusion and analysis of thermal and visible images in diabetes mellitus using machine learning techniques

The study aimed to achieve the following objectives: (1) to perform the fusion of thermal and visible tongue images with various fusion rules of discrete wavelet transform (DWT) to classify diabetes and normal subjects; (2) to obtain the statistical features in the required region of interest from the tongue image before and after fusion; (3) to distinguish the healthy and diabetes using fused tongue images based on deep and machine learning algorithms. The study participants comprised of 80 normal subjects and age- and sex-matched 80 diabetes patients. The biochemical tests such as fasting glucose, postprandial, Hba1c are taken for all the participants. The visible and thermal tongue images are acquired using digital single lens reference camera and thermal infrared cameras, respectively. The digital and thermal tongue images are fused based on the wavelet transform method. Then Gray level co-occurrence matrix features are extracted individually from the visible, thermal, and fused tongue images. The machine learning classifiers and deep learning networks such as VGG16 and ResNet50 was used to classify the normal and diabetes mellitus. Image quality metrics are implemented to compare the classifiers' performance before and after fusion. Support vector machine outperformed the machine learning classifiers, well after fusion with an accuracy of 88.12% compared to before the fusion process (Thermal-84.37%; Visible-63.1%). VGG16 produced the classification accuracy of 94.37% after fusion and attained 90.62% and 85% before fusion of individual thermal and visible tongue images, respectively. Therefore, this study results indicates that fused tongue images might be used as a non-contact elemental tool for pre-screening type II diabetes mellitus.

An innovative artificial intelligence-based method to compress complex models into explainable, model-agnostic and reduced decision support systems with application to healthcare (NEAR)

BACKGROUND AND OBJECTIVE

In everyday clinical practice, medical decision is currently based on clinical guidelines which are often static and rigid, and do not account for population variability, while individualized, patient-oriented decision and/or treatment are the paradigm change necessary to enter into the era of precision medicine. Most of the limitations of a guideline-based system could be overcome through the adoption of Clinical Decision Support Systems (CDSSs) based on Artificial Intelligence (AI) algorithms. However, the black-box nature of AI algorithms has hampered a large adoption of AI-based CDSSs in clinical practice. In this study, an innovative AI-based method to compress AI-based prediction models into explainable, model-agnostic, and reduced decision support systems (NEAR) with application to healthcare is presented and validated.

METHODS

NEAR is based on the Shapley Additive Explanations framework and can be applied to complex input models to obtain the contributions of each input feature to the output. Technically, the simplified NEAR models approximate contributions from input features using a custom library and merge them to determine the final output. Finally, NEAR estimates the confidence error associated with the single input feature contributing to the final score, making the result more interpretable. Here, NEAR is evaluated on a clinical real-world use case, the mortality prediction in patients who experienced Acute Coronary Syndrome (ACS), applying three different Machine Learning/Deep Learning models as implementation examples.

RESULTS

NEAR, when applied to the ACS use case, exhibits performances like the ones of the AI-based model from which it is derived, as in the case of the Adaptive Boosting classifier, whose Area Under the Curve is not statistically different from the NEAR one, even the model's simplification. Moreover, NEAR comes with intrinsic explainability and modularity, as it can be tested on the developed web application platform (https://neardashboard.pythonanywhere.com/).

CONCLUSIONS

An explainable and reliable CDSS tailored to single-patient analysis has been developed. The proposed AI-based system has the potential to be used alongside the clinical guidelines currently employed in the medical setting making them more personalized and dynamic and assisting doctors in taking their everyday clinical decisions.

Maternal diet quality and associations with plasma lipid profiles and pregnancy-related cardiometabolic health

PURPOSE

To assess the relationship of early pregnancy maternal diet quality (DQ) with maternal plasma lipids and indicators of cardiometabolic health, including blood pressure (BP), gestational diabetes mellitus (GDM) and gestational weight gain (GWG).

METHODS

Women (n = 215) aged 18-40 years with singleton pregnancies were recruited at 10-20 weeks gestation. Diet quality was assessed by the Dietary Guideline Index, calculated at early ([mean ± SD]) (15 ± 3 weeks) and late (35 ± 2 weeks) pregnancy. Lipidomic analysis was performed, and 698 species across 37 lipid classes were measured from plasma blood samples collected at early (15 ± 3 weeks) and mid (27 ± 3 weeks)-pregnancy. Clinical measures (BP, GDM diagnosis, weight) and blood samples were collected across pregnancy. Multiple linear and logistic regression models assessed associations of early pregnancy DQ with plasma lipids at early and mid-pregnancy, BP at three antenatal visits, GDM diagnosis and total GWG.

RESULTS

Maternal DQ scores ([mean ± SD]) decreased significantly from early (70.7 ± 11.4) to late pregnancy (66.5 ± 12.6) (p < 0.0005). At a false discovery rate of 0.2, early pregnancy DQ was significantly associated with 13 plasma lipids at mid-pregnancy, including negative associations with six triglycerides (TGs); TG(54:0)[NL-18:0] (neutral loss), TG(50:1)[NL-14:0], TG(48:0)[NL-18:0], TG(52:1)[NL-18:0], TG(54:1)[NL-18:1], TG(50:0)[NL-18:0]. No statistically significant associations were found between early pregnancy DQ and BP, GDM or GWG.

CONCLUSION

Maternal diet did not adhere to Australian Dietary Guidelines. Diet quality was inversely associated with multiple plasma TGs. This study provides novel insights into the relationship between DQ, lipid biomarkers and cardiometabolic health during pregnancy.

Harnessing the power of clinical decision support systems: challenges and opportunities

Clinical decision support systems (CDSSs) are increasingly integrated into healthcare settings to improve patient outcomes, reduce medical errors and enhance clinical efficiency by providing clinicians with evidence-based recommendations at the point of care. However, the adoption and optimisation of these systems remain a challenge. This review aims to provide an overview of the current state of CDSS, discussing their development, implementation, benefits, limitations and future directions. We also explore the potential for enhancing their effectiveness and provide an outlook for future developments in this field. There are several challenges in CDSS implementation, including data privacy concerns, system integration and clinician acceptance. While CDSS have demonstrated significant potential, their adoption and optimisation remain a challenge.

A Mobile App That Addresses Interpretability Challenges in Machine Learning-Based Diabetes Predictions: Survey-Based User Study

BACKGROUND

Machine learning approaches, including deep learning, have demonstrated remarkable effectiveness in the diagnosis and prediction of diabetes. However, these approaches often operate as opaque black boxes, leaving health care providers in the dark about the reasoning behind predictions. This opacity poses a barrier to the widespread adoption of machine learning in diabetes and health care, leading to confusion and eroding trust.

OBJECTIVE

This study aimed to address this critical issue by developing and evaluating an explainable artificial intelligence (AI) platform, XAI4Diabetes, designed to empower health care professionals with a clear understanding of AI-generated predictions and recommendations for diabetes care. XAI4Diabetes not only delivers diabetes risk predictions but also furnishes easily interpretable explanations for complex machine learning models and their outcomes.

METHODS

XAI4Diabetes features a versatile multimodule explanation framework that leverages machine learning, knowledge graphs, and ontologies. The platform comprises the following four essential modules: (1) knowledge base, (2) knowledge matching, (3) prediction, and (4) interpretation. By harnessing AI techniques, XAI4Diabetes forecasts diabetes risk and provides valuable insights into the prediction process and outcomes. A structured, survey-based user study assessed the app's usability and influence on participants' comprehension of machine learning predictions in real-world patient scenarios.

RESULTS

A prototype mobile app was meticulously developed and subjected to thorough usability studies and satisfaction surveys. The evaluation study findings underscore the substantial improvement in medical professionals' comprehension of key aspects, including the (1) diabetes prediction process, (2) data sets used for model training, (3) data features used, and (4) relative significance of different features in prediction outcomes. Most participants reported heightened understanding of and trust in AI predictions following their use of XAI4Diabetes. The satisfaction survey results further revealed a high level of overall user satisfaction with the tool.

CONCLUSIONS

This study introduces XAI4Diabetes, a versatile multi-model explainable prediction platform tailored to diabetes care. By enabling transparent diabetes risk predictions and delivering interpretable insights, XAI4Diabetes empowers health care professionals to comprehend the AI-driven decision-making process, thereby fostering transparency and trust. These advancements hold the potential to mitigate biases and facilitate the broader integration of AI in diabetes care.

Impact of visceral obesity on infectious complications after resection for colorectal cancer: a retrospective cohort study

OBJECTIVES

To explore the impact of visceral obesity (VO) measured by preoperative abdominal computed tomography (CT) on postoperative infectious complications for colorectal cancer (CRC) patients and establish a predictive model.

METHODS

Patients who underwent resection for colorectal cancer between January 2015 and January 2021 were enrolled in this study. All patients were measured for body mass index (BMI) and visceral fat area (VFA) preoperatively. Infectious complications were compared between the different groups according to BMI and VO categories. Univariate and multivariate logistic regression were used to analyze whether VO was an independent risk factor for postoperative infectious complications. According to the results of logistic regression, six machine learning approaches were used to establish predictive models and perform internal validation. The best-performing model was interpreted by the SHAPley Additive exPlanations value.

RESULTS

Approximately 64.81% of 520 patients had VO. VO was significantly connected with postoperative infectious complications (P < 0.001), coronary heart disease (P = 0.004), cerebral infarction (P = 0.001), hypertension (P < 0.001), diabetes (P < 0.001), and fatty liver (P < 0.001). The rates of wound infection (P = 0.048), abdominal or pelvic infection (P = 0.006), and pneumonia (P = 0.008) increased obviously in patients with VO. Compared to the low BMI group, a high BMI was found to be significantly associated with hypertension (P=0.007), fatty liver (P＜0.001), and a higher rate of postoperative infection (P=0.003). The results of logistic regression revealed that VO (OR = 2.01, 95% CI 1.17 ~ 3.48, P = 0.012), operation time ≥ 4 h (OR = 2.52, 95% CI 1.60 ~ 3.97, P < 0.001), smoking (OR = 2.04, 95% CI 1.16 ~ 3.59, P = 0.014), ostomy (OR = 1.65, 95% CI 1.04 ~ 2.61, P = 0.033), and chronic obstructive pulmonary disease (COPD) (OR = 2.23, 95% CI 1.09 ~ 4.57, P = 0.029) were independent risk factors. The light gradient boosting machine (LGBM) model displayed the largest area under the receiver operating characteristic curve (AUC) (0.74, 95% CI 0.68 ~ 0.81).

CONCLUSIONS

In this study, VO was superior to BMI in evaluating the influence of obesity on metabolic comorbidities and postoperative infectious complications in colorectal cancer patients.

Synthesizing Electronic Health Records for Predictive Models in Low-Middle-Income Countries (LMICs)

The spread of machine learning models, coupled with by the growing adoption of electronic health records (EHRs), has opened the door for developing clinical decision support systems. However, despite the great promise of machine learning for healthcare in low-middle-income countries (LMICs), many data-specific limitations, such as the small size and irregular sampling, hinder the progress in such applications. Recently, deep generative models have been proposed to generate realistic-looking synthetic data, including EHRs, by learning the underlying data distribution without compromising patient privacy. In this study, we first use a deep generative model to generate synthetic data based on a small dataset (364 patients) from a LMIC setting. Next, we use synthetic data to build models that predict the onset of hospital-acquired infections based on minimal information collected at patient ICU admission. The performance of the diagnostic model trained on the synthetic data outperformed models trained on the original and oversampled data using techniques such as SMOTE. We also experiment with varying the size of the synthetic data and observe the impact on the performance and interpretability of the models. Our results show the promise of using deep generative models in enabling healthcare data owners to develop and validate models that serve their needs and applications, despite limitations in dataset size.

Survey of Explainable AI Techniques in Healthcare

Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient's symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.

Artificial Intelligence for Predicting and Diagnosing Complications of Diabetes

Artificial intelligence can use real-world data to create models capable of making predictions and medical diagnosis for diabetes and its complications. The aim of this commentary article is to provide a general perspective and present recent advances on how artificial intelligence can be applied to improve the prediction and diagnosis of six significant complications of diabetes including (1) gestational diabetes, (2) hypoglycemia in the hospital, (3) diabetic retinopathy, (4) diabetic foot ulcers, (5) diabetic peripheral neuropathy, and (6) diabetic nephropathy.

Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011-2022)

BACKGROUND AND OBJECTIVES

Artificial intelligence (AI) has branched out to various applications in healthcare, such as health services management, predictive medicine, clinical decision-making, and patient data and diagnostics. Although AI models have achieved human-like performance, their use is still limited because they are seen as a black box. This lack of trust remains the main reason for their low use in practice, especially in healthcare. Hence, explainable artificial intelligence (XAI) has been introduced as a technique that can provide confidence in the model's prediction by explaining how the prediction is derived, thereby encouraging the use of AI systems in healthcare. The primary goal of this review is to provide areas of healthcare that require more attention from the XAI research community.

METHODS

Multiple journal databases were thoroughly searched using PRISMA guidelines 2020. Studies that do not appear in Q1 journals, which are highly credible, were excluded.

RESULTS

In this review, we surveyed 99 Q1 articles covering the following XAI techniques: SHAP, LIME, GradCAM, LRP, Fuzzy classifier, EBM, CBR, rule-based systems, and others.

CONCLUSION

We discovered that detecting abnormalities in 1D biosignals and identifying key text in clinical notes are areas that require more attention from the XAI research community. We hope this is review will encourage the development of a holistic cloud system for a smart city.

Deep-spindle: An automated sleep spindle detection system for analysis of infant sleep spindles

BACKGROUND

Sleep spindles are an indicator of the development and integrity of the central nervous system in infants. Identifying sleep spindles manually in EEG is time-consuming and typically requires experienced experts. Automated detection of sleep spindles would greatly facilitate this analysis. Deep learning methods have been widely used recently in EEG analysis.

METHOD

We have developed a deep learning-based automated sleep spindle detection system, Deep-spindle, which employs a convolutional neural network (CNN) combined with a bidirectional Long Short-Term Memory (LSTM) network, which could assist in the analysis of infant sleep spindles. Deep-spindle was trained on the EEGs of ex-term infants to estimate the number and duration of sleep spindles. The ex-term EEG on channel F4-C4 was split into training (N=81) and validation (N=30) sets. An additional 30 ex-term EEG and 54 ex-preterm infant EEGs (channel F4-C4 and F3-C3) were used as an independent test set.

RESULT

Deep-spindle detected the number of sleep spindles with 91.9% to 96.5% sensitivity and 95.3% to 96.7% specificity, and estimated sleep spindle duration with a percent error of 13.1% to 19.1% in the independent test set. For each detected spindle event, the user is presented with amplitude, power spectral density and the spectrogram of the corresponding spindle EEG, and the probability of the event being a sleep spindle event, providing the user with insight into why the event is predicted as a sleep spindle to provide confidence in the predictions.

CONCLUSION

The Deep-spindle system can reduce physicians' workload, demonstrating the potential to assist physicians in the automated analysis of sleep spindles in infants.

A rapid review of machine learning approaches for telemedicine in the scope of COVID-19

The COVID-19 pandemic has rapidly spread around the world. The rapid transmission of the virus is a threat that hinders the ability to contain the disease propagation. The pandemic forced widespread conversion of in-person to virtual care delivery through telemedicine. Given this gap, this article aims at providing a literature review of machine learning-based telemedicine applications to mitigate COVID-19. A rapid review of the literature was conducted in six electronic databases published from 2015 through 2020. The process of data extraction was documented using a PRISMA flowchart for inclusion and exclusion of studies. As a result, the literature search identified 1.733 articles, from which 16 articles were included in the review. We developed an updated taxonomy and identified challenges, open questions, and current data types. Our taxonomy and discussion contribute with a significant degree of coverage from subjects related to the use of machine learning to improve telemedicine in response to the COVID-19 pandemic. The evidence identified by this rapid review suggests that machine learning, in combination with telemedicine, can provide a strategy to control outbreaks by providing smart triage of patients and remote monitoring. Also, the use of telemedicine during future outbreaks could be further explored and refined.

A Clinical Decision Support System for the Prediction of Quality of Life in ALS

Amyotrophic Lateral Sclerosis (ALS), also known as Motor Neuron Disease (MND), is a rare and fatal neurodegenerative disease. As ALS is currently incurable, the aim of the treatment is mainly to alleviate symptoms and improve quality of life (QoL). We designed a prototype Clinical Decision Support System (CDSS) to alert clinicians when a person with ALS is experiencing low QoL in order to inform and personalise the support they receive. Explainability is important for the success of a CDSS and its acceptance by healthcare professionals. The aim of this work isto announce our prototype (C-ALS), supported by a first short evaluation of its explainability. Given the lack of similar studies and systems, this work is a valid proof-of-concept that will lead to future work. We developed a CDSS that was evaluated by members of the team of healthcare professionals that provide care to people with ALS in the ALS/MND Multidisciplinary Clinic in Dublin, Ireland. We conducted a user study where participants were asked to review the CDSS and complete a short survey with a focus on explainability. Healthcare professionals demonstrated some uncertainty in understanding the system’s output. Based on their feedback, we altered the explanation provided in the updated version of our CDSS. C-ALS provides local explanations of its predictions in a post-hoc manner, using SHAP (SHapley Additive exPlanations). The CDSS predicts the risk of low QoL in the form of a probability, a bar plot shows the feature importance for the specific prediction, along with some verbal guidelines on how to interpret the results. Additionally, we provide the option of a global explanation of the system’s function in the form of a bar plot showing the average importance of each feature. C-ALS is available online for academic use.