Tackling prediction uncertainty in machine learning for healthcare

The Fourth Industrial Revolution: Its Impact on Artificial Intelligence and Medicine in Developing Countries

Artificial intelligence (AI) is the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings. Artificial intelligence can be both a blessing and a curse, and potentially a double-edged sword if not carefully wielded. While it holds massive potential benefits to humans-particularly in healthcare by assisting in treatment of diseases, surgeries, record keeping, and easing the lives of both patients and doctors, its misuse has potential for harm through impact of biases, unemployment, breaches of privacy, and lack of accountability to mention a few. In this article, we discuss the fourth industrial revolution, through a focus on the core of this phenomenon, artificial intelligence. We outline what the fourth industrial revolution is, its basis around AI, and how this infiltrates human lives and society, akin to a transcendence. We focus on the potential dangers of AI and the ethical concerns it brings about particularly in developing countries in general and conflict zones in particular, and we offer potential solutions to such dangers. While we acknowledge the importance and potential of AI, we also call for cautious reservations before plunging straight into the exciting world of the future, one which we long have heard of only in science fiction movies.

Ηand dexterities assessment in stroke patients based on augmented reality and machine learning through a box and block test

A popular and widely suggested measure for assessing unilateral hand motor skills in stroke patients is the box and block test (BBT). Our study aimed to create an augmented reality enhanced version of the BBT (AR-BBT) and evaluate its correlation to the original BBT for stroke patients. Following G-power analysis, clinical examination, and inclusion-exclusion criteria, 31 stroke patients were included in this study. AR-BBT was developed using the Open Source Computer Vision Library (OpenCV). The MediaPipe's hand tracking library uses a palm and a hand landmark machine learning model to detect and track hands. A computer and a depth camera were employed in the clinical evaluation of AR-BBT following the principles of traditional BBT. A strong correlation was achieved between the number of blocks moved in the BBT and the AR-BBT on the hemiplegic side (Pearson correlation = 0.918) and a positive statistically significant correlation (p = 0.000008). The conventional BBT is currently the preferred assessment method. However, our approach offers an advantage, as it suggests that an AR-BBT solution could remotely monitor the assessment of a home-based rehabilitation program and provide additional hand kinematic information for hand dexterities in AR environment conditions. Furthermore, it employs minimal hardware equipment.

Revolutionizing diagnostic pathology: The emergence and impact of artificial intelligence-what doesn't kill you makes you stronger?

This study explored the integration and impact of artificial intelligence (AI) in diagnostic pathology, particularly dermatopathology, assessing its challenges and potential solutions for global health care enhancement. A comprehensive literature search in PubMed and Google Scholar, conducted on March 30, 2023, and using terms related to AI, pathology, and machine learning, yielded 44 relevant publications. These were analyzed under themes including the evolution of deep learning in pathology, AI's role in replacing pathologists, development challenges of diagnostic algorithms, clinical implementation hurdles, strategies for practical application in dermatopathology, and future prospects of AI in this field. The findings highlight AI's transformative potential in pathology, underscore the need for ongoing research, collaboration, and regulatory dialogue, and emphasize the importance of addressing the ethical and practical challenges in AI implementation for improved global health care outcomes.

Aleatoric and epistemic uncertainty extraction of patient-specific deep learning-based dose predictions in LDR prostate brachytherapy

Objective.In brachytherapy, deep learning (DL) algorithms have shown the capability of predicting 3D dose volumes. The reliability and accuracy of such methodologies remain under scrutiny for prospective clinical applications. This study aims to establish fast DL-based predictive dose algorithms for low-dose rate (LDR) prostate brachytherapy and to evaluate their uncertainty and stability.Approach.Data from 200 prostate patients, treated with125I sources, was collected. The Monte Carlo (MC) ground truth dose volumes were calculated with TOPAS considering the interseed effects and an organ-based material assignment. Two 3D convolutional neural networks, UNet and ResUNet TSE, were trained using the patient geometry and the seed positions as the input data. The dataset was randomly split into training (150), validation (25) and test (25) sets. The aleatoric (associated with the input data) and epistemic (associated with the model) uncertainties of the DL models were assessed.Main results.For the full test set, with respect to the MC reference, the predicted prostateD90metric had mean differences of -0.64% and 0.08% for the UNet and ResUNet TSE models, respectively. In voxel-by-voxel comparisons, the average global dose difference ratio in the [-1%, 1%] range included 91.0% and 93.0% of voxels for the UNet and the ResUNet TSE, respectively. One forward pass or prediction took 4 ms for a 3D dose volume of 2.56 M voxels (128 × 160 × 128). The ResUNet TSE model closely encoded the well-known physics of the problem as seen in a set of uncertainty maps. The ResUNet TSE rectum D2cchad the largest uncertainty metric of 0.0042.Significance.The proposed DL models serve as rapid dose predictors that consider the patient anatomy and interseed attenuation effects. The derived uncertainty is interpretable, highlighting areas where DL models may struggle to provide accurate estimations. The uncertainty analysis offers a comprehensive evaluation tool for dose predictor model assessment.

Large language models streamline automated machine learning for clinical studies

A knowledge gap persists between machine learning (ML) developers (e.g., data scientists) and practitioners (e.g., clinicians), hampering the full utilization of ML for clinical data analysis. We investigated the potential of the ChatGPT Advanced Data Analysis (ADA), an extension of GPT-4, to bridge this gap and perform ML analyses efficiently. Real-world clinical datasets and study details from large trials across various medical specialties were presented to ChatGPT ADA without specific guidance. ChatGPT ADA autonomously developed state-of-the-art ML models based on the original study's training data to predict clinical outcomes such as cancer development, cancer progression, disease complications, or biomarkers such as pathogenic gene sequences. Following the re-implementation and optimization of the published models, the head-to-head comparison of the ChatGPT ADA-crafted ML models and their respective manually crafted counterparts revealed no significant differences in traditional performance metrics (p ≥ 0.072). Strikingly, the ChatGPT ADA-crafted ML models often outperformed their counterparts. In conclusion, ChatGPT ADA offers a promising avenue to democratize ML in medicine by simplifying complex data analyses, yet should enhance, not replace, specialized training and resources, to promote broader applications in medical research and practice.

A Deep Learning Model for Screening Computed Tomography Imaging for Thyroid Eye Disease and Compressive Optic Neuropathy

Purpose

Thyroid eye disease (TED) is an autoimmune condition with an array of clinical manifestations, which can be complicated by compressive optic neuropathy. It is important to identify patients with TED early to ensure close monitoring and treatment to prevent potential permanent disability or vision loss. Deep learning artificial intelligence (AI) algorithms have been utilized in ophthalmology and in other fields of medicine to detect disease. This study aims to introduce a deep learning model to evaluate orbital computed tomography (CT) images for the presence of TED and potential compressive optic neuropathy.

Design

Retrospective review and deep learning algorithm modeling.

Subjects

Patients with TED with dedicated orbital CT scans and with an examination by an oculoplastic surgeon over a 10-year period at a single academic institution. Patients with no TED and normal CTs were used as normal controls. Those with other diagnoses, such as tumors or other inflammatory processes, were excluded.

Methods

Orbital CTs were preprocessed and adopted for the Visual Geometry Group-16 network to distinguish patients with no TED, mild TED, and severe TED with compressive optic neuropathy. The primary model included training and testing of all 3 conditions. Binary model performance was also evaluated. An oculoplastic surgeon was also similarly tested with single and serial images for comparison.

Main Outcome Measures

Accuracy of deep learning model discernment of region of interest for CT scans to distinguish TED versus normal control, as well as TED with clinical signs of optic neuropathy.

Results

A total of 1187 photos from 141 patients were used to develop the AI model. The primary model trained on patients with no TED, mild TED, and severe TED had 89.5% accuracy (area under the curve: range, 0.96-0.99) in distinguishing patients with these clinical categories. In comparison, testing of an oculoplastic surgeon in these 3 categories showed decreased accuracy (70.0% accuracy in serial image testing).

Conclusions

The deep learning model developed in the study can accurately detect TED and further detect TED with clinical signs of optic neuropathy based on orbital CT. The model proved superior compared with human expert grading. With further optimization and validation, this TED deep learning model could help guide frontline health care providers in the detection of TED and help stratify the urgency of a referral to an oculoplastic surgeon and endocrinologist.

Financial Disclosures

The authors have no proprietary or commercial interest in any materials discussed in this article.

Ensemble Geometric Deep Learning of Aqueous Solubility

Geometric deep learning is one of the main workhorses for harnessing the power of big data to predict molecular properties such as aqueous solubility, which is key to the pharmacokinetic improvement of drug candidates. Two ensembles of graph neural network architectures were built, one based on spectral convolution and the other on spatial convolution. The pretrained models, denoted respectively as SolNet-GCN and SolNet-GAT, significantly outperformed the existing neural networks benchmarked on a validation set of 207 molecules. The SolNet-GCN model demonstrated the best performance on both the training and validation sets, with RMSE values of 0.53 and 0.72 log molar unit and Pearson r2 values of 0.95 and 0.75, respectively. Further, the ranking power of the SolNet models agreed well with a QM-based thermodynamic cycle approach at the PBE-vdW level of theory on a series of benzophenylurea derivatives and a series of benzodiazepine derivatives. Nevertheless, testing the resultant models on a set of inhibitors of the macrophage migration inhibitory factor (MIF) illustrated that the inclusion of atomic attributes to discriminate atoms with a higher tendency to form intermolecular hydrogen bonds in the crystalline state and to identify planar or nonplanar substructures can be beneficial for the prediction of aqueous solubility.

Identifying cancer-associated leukocyte profiles using high-resolution flow cytometry screening and machine learning

Background

Machine learning (ML) is a valuable tool with the potential to aid clinical decision making. Adoption of ML to this end requires data that reliably correlates with the clinical outcome of interest; the advantage of ML is that it can model these correlations from complex multiparameter data sets that can be difficult to interpret conventionally. While currently available clinical data can be used in ML for this purpose, there exists the potential to discover new "biomarkers" that will enhance the effectiveness of ML in clinical decision making. Since the interaction of the immune system and cancer is a hallmark of tumor establishment and progression, one potential area for cancer biomarker discovery is through the investigation of cancer-related immune cell signatures. Hence, we hypothesize that blood immune cell signatures can act as a biomarker for cancer progression.

Methods

To probe this, we have developed and tested a multiparameter cell-surface marker screening pipeline, using flow cytometry to obtain high-resolution systemic leukocyte population profiles that correlate with detection and characterization of several cancers in murine syngeneic tumor models.

Results

We discovered a signature of several blood leukocyte subsets, the most notable of which were monocyte subsets, that could be used to train CATboost ML models to predict the presence and type of cancer present in the animals.

Conclusions

Our findings highlight the potential utility of a screening approach to identify robust leukocyte biomarkers for cancer detection and characterization. This pipeline can easily be adapted to screen for cancer specific leukocyte markers from the blood of cancer patient.