Intricacies of Human-AI Interaction in Dynamic Decision-Making for Precision Oncology: A Case Study in Response-Adaptive Radiotherapy.

Background: Adaptive treatment strategies that can dynamically react to individual cancer progression can provide effective personalized care. Longitudinal multi-omics information, paired with an artificially intelligent clinical decision support system (AI-CDSS) can assist clinicians in determining optimal therapeutic options and treatment adaptations. However, AI-CDSS is not perfectly accurate, as such, clinicians' over/under reliance on AI may lead to unintended consequences, ultimately failing to develop optimal strategies. To investigate such collaborative decision-making process, we conducted a Human-AI interaction case study on response-adaptive radiotherapy (RT). Methods: We designed and conducted a two-phase study for two disease sites and two treatment modalities-adaptive RT for non-small cell lung cancer (NSCLC) and adaptive stereotactic body RT for hepatocellular carcinoma (HCC)-in which clinicians were asked to consider mid-treatment modification of the dose per fraction for a number of retrospective cancer patients without AI-support (Unassisted Phase) and with AI-assistance (AI-assisted Phase). The AI-CDSS graphically presented trade-offs in tumor control and the likelihood of toxicity to organs at risk, provided an optimal recommendation, and associated model uncertainties. In addition, we asked for clinicians' decision confidence level and trust level in individual AI recommendations and encouraged them to provide written remarks. We enrolled 13 evaluators (radiation oncology physicians and residents) from two medical institutions located in two different states, out of which, 4 evaluators volunteered in both NSCLC and HCC studies, resulting in a total of 17 completed evaluations (9 NSCLC, and 8 HCC). To limit the evaluation time to under an hour, we selected 8 treated patients for NSCLC and 9 for HCC, resulting in a total of 144 sets of evaluations (72 from NSCLC and 72 from HCC). Evaluation for each patient consisted of 8 required inputs and 2 optional remarks, resulting in up to a total of 1440 data points. Results: AI-assistance did not homogeneously influence all experts and clinical decisions. From NSCLC cohort, 41 (57%) decisions and from HCC cohort, 34 (47%) decisions were adjusted after AI assistance. Two evaluations (12%) from the NSCLC cohort had zero decision adjustments, while the remaining 15 (88%) evaluations resulted in at least two decision adjustments. Decision adjustment level positively correlated with dissimilarity in decision-making with AI [NSCLC: ρ = 0.53 ( p < 0.001); HCC: ρ = 0.60 ( p < 0.001)] indicating that evaluators adjusted their decision closer towards AI recommendation. Agreement with AI-recommendation positively correlated with AI Trust Level [NSCLC: ρ = 0.59 ( p < 0.001); HCC: ρ = 0.7 ( p < 0.001)] indicating that evaluators followed AI's recommendation if they agreed with that recommendation. The correlation between decision confidence changes and decision adjustment level showed an opposite trend [NSCLC: ρ = -0.24 ( p = 0.045), HCC: ρ = 0.28 ( p = 0.017)] reflecting the difference in behavior due to underlying differences in disease type and treatment modality. Decision confidence positively correlated with the closeness of decisions to the standard of care (NSCLC: 2 Gy/fx; HCC: 10 Gy/fx) indicating that evaluators were generally more confident in prescribing dose fractionations more similar to those used in standard clinical practice. Inter-evaluator agreement increased with AI-assistance indicating that AI-assistance can decrease inter-physician variability. The majority of decisions were adjusted to achieve higher tumor control in NSCLC and lower normal tissue complications in HCC. Analysis of evaluators' remarks indicated concerns for organs at risk and RT outcome estimates as important decision-making factors. Conclusions: Human-AI interaction depends on the complex interrelationship between expert's prior knowledge and preferences, patient's state, disease site, treatment modality, model transparency, and AI's learned behavior and biases. The collaborative decision-making process can be summarized as follows: (i) some clinicians may not believe in an AI system, completely disregarding its recommendation, (ii) some clinicians may believe in the AI system but will critically analyze its recommendations on a case-by-case basis; (iii) when a clinician finds that the AI recommendation indicates the possibility for better outcomes they will adjust their decisions accordingly; and (iv) When a clinician finds that the AI recommendation indicate a worse possible outcome they will disregard it and seek their own alternative approach.

Classifying migraine using PET compressive big data analytics of brain's µ-opioid and D2/D3 dopamine neurotransmission.

Introduction: Migraine is a common and debilitating pain disorder associated with dysfunction of the central nervous system. Advanced magnetic resonance imaging (MRI) studies have reported relevant pathophysiologic states in migraine. However, its molecular mechanistic processes are still poorly understood in vivo. This study examined migraine patients with a novel machine learning (ML) method based on their central µ-opioid and dopamine D2/D3 profiles, the most critical neurotransmitters in the brain for pain perception and its cognitive-motivational interface. Methods: We employed compressive Big Data Analytics (CBDA) to identify migraineurs and healthy controls (HC) in a large positron emission tomography (PET) dataset. 198 PET volumes were obtained from 38 migraineurs and 23 HC during rest and thermal pain challenge. 61 subjects were scanned with the selective µ-opioid receptor (µOR) radiotracer [11C]Carfentanil, and 22 with the selective dopamine D2/D3 receptor (DOR) radiotracer [11C]Raclopride. PET scans were recast into a 1D array of 510,340 voxels with spatial and intensity filtering of non-displaceable binding potential (BPND), representing the receptor availability level. We then performed data reduction and CBDA to power rank the predictive brain voxels. Results: CBDA classified migraineurs from HC with accuracy, sensitivity, and specificity above 90% for whole-brain and region-of-interest (ROI) analyses. The most predictive ROIs for µOR were the insula (anterior), thalamus (pulvinar, medial-dorsal, and ventral lateral/posterior nuclei), and the putamen. The latter, putamen (anterior), was also the most predictive for migraine regarding DOR D2/D3 BPND levels. Discussion: CBDA of endogenous µ-opioid and D2/D3 dopamine dysfunctions in the brain can accurately identify a migraine patient based on their receptor availability across key sensory, motor, and motivational processing regions. Our ML-based findings in the migraineur's brain neurotransmission partly explain the severe impact of migraine suffering and associated neuropsychiatric comorbidities.

Generalizable prediction of childhood ADHD symptoms from neurocognitive testing and youth characteristics.

Childhood attention-deficit/hyperactivity disorder (ADHD) symptoms are believed to result from disrupted neurocognitive development. However, evidence for the clinical and predictive value of neurocognitive assessments in this context has been mixed, and there have been no large-scale efforts to quantify their potential for use in generalizable models that predict individuals' ADHD symptoms in new data. Using data drawn from the Adolescent Brain Cognitive Development Study (ABCD), a consortium that recruited a diverse sample of over 10,000 youth (ages 9-10 at baseline) across 21 U.S. sites, we develop and test cross-validated machine learning models for predicting youths' ADHD symptoms using neurocognitive abilities, demographics, and child and family characteristics. Models used baseline demographic and biometric measures, geocoded neighborhood data, youth reports of child and family characteristics, and neurocognitive tests to predict parent- and teacher-reported ADHD symptoms at the 1-year and 2-year follow-up time points. Predictive models explained 15-20% of the variance in 1-year ADHD symptoms for ABCD Study sites that were left out of the model-fitting process and 12-13% of the variance in 2-year ADHD symptoms. Models displayed high generalizability across study sites and trivial loss of predictive power when transferred from training data to left-out data. Features from multiple domains contributed meaningfully to prediction, including neurocognition, sex, self-reported impulsivity, parental monitoring, and screen time. This work quantifies the information value of neurocognitive abilities and other child characteristics for predicting ADHD symptoms and provides a foundational method for predicting individual youths' symptoms in new data across contexts.

Machine Learning-Based Prediction of Mental Well-Being Using Health Behavior Data from University Students.

BACKGROUND: Since the onset of the COVID-19 pandemic in early 2020, the importance of timely and effective assessment of mental well-being has increased dramatically. Machine learning (ML) algorithms and artificial intelligence (AI) techniques can be harnessed for early detection, prognostication and prediction of negative psychological well-being states. METHODS: We used data from a large, multi-site cross-sectional survey consisting of 17 universities in Southeast Asia. This research work models mental well-being and reports on the performance of various machine learning algorithms, including generalized linear models, k-nearest neighbor, naïve Bayes, neural networks, random forest, recursive partitioning, bagging, and boosting. RESULTS: Random Forest and adaptive boosting algorithms achieved the highest accuracy for identifying negative mental well-being traits. The top five most salient features associated with predicting poor mental well-being include the number of sports activities per week, body mass index, grade point average (GPA), sedentary hours, and age. CONCLUSIONS: Based on the reported results, several specific recommendations and suggested future work are discussed. These findings may be useful to provide cost-effective support and modernize mental well-being assessment and monitoring at the individual and university level.

Multimodal Stereotactic Brain Tumor Segmentation Using 3D-Znet.

Stereotactic brain tumor segmentation based on 3D neuroimaging data is a challenging task due to the complexity of the brain architecture, extreme heterogeneity of tumor malformations, and the extreme variability of intensity signal and noise distributions. Early tumor diagnosis can help medical professionals to select optimal medical treatment plans that can potentially save lives. Artificial intelligence (AI) has previously been used for automated tumor diagnostics and segmentation models. However, the model development, validation, and reproducibility processes are challenging. Often, cumulative efforts are required to produce a fully automated and reliable computer-aided diagnostic system for tumor segmentation. This study proposes an enhanced deep neural network approach, the 3D-Znet model, based on the variational autoencoder-autodecoder Znet method, for segmenting 3D MR (magnetic resonance) volumes. The 3D-Znet artificial neural network architecture relies on fully dense connections to enable the reuse of features on multiple levels to improve model performance. It consists of four encoders and four decoders along with the initial input and the final output blocks. Encoder-decoder blocks in the network include double convolutional 3D layers, 3D batch normalization, and an activation function. These are followed by size normalization between inputs and outputs and network concatenation across the encoding and decoding branches. The proposed deep convolutional neural network model was trained and validated using a multimodal stereotactic neuroimaging dataset (BraTS2020) that includes multimodal tumor masks. Evaluation of the pretrained model resulted in the following dice coefficient scores: Whole Tumor (WT) = 0.91, Tumor Core (TC) = 0.85, and Enhanced Tumor (ET) = 0.86. The performance of the proposed 3D-Znet method is comparable to other state-of-the-art methods. Our protocol demonstrates the importance of data augmentation to avoid overfitting and enhance model performance.

A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS).

Involvement of many variables, uncertainty in treatment response, and inter-patient heterogeneity challenge objective decision-making in dynamic treatment regime (DTR) in oncology. Advanced machine learning analytics in conjunction with information-rich dense multi-omics data have the ability to overcome such challenges. We have developed a comprehensive artificial intelligence (AI)-based optimal decision-making framework for assisting oncologists in DTR. In this work, we demonstrate the proposed framework to Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications by developing an interactive software tool entitled Adaptive Radiotherapy Clinical Decision Support (ARCliDS). ARCliDS is composed of two main components: Artifcial RT Environment (ARTE) and Optimal Decision Maker (ODM). ARTE is designed as a Markov decision process and modeled via supervised learning. Given a patient's pre- and during-treatment information, ARTE can estimate treatment outcomes for a selected daily dosage value (radiation fraction size). ODM is formulated using reinforcement learning and is trained on ARTE. ODM can recommend optimal daily dosage adjustments to maximize the tumor local control probability and minimize the side effects. Graph Neural Networks (GNN) are applied to exploit the inter-feature relationships for improved modeling performance and a novel double GNN architecture is designed to avoid nonphysical treatment response. Datasets of size 117 and 292 were available from two clinical trials on adaptive RT in non-small cell lung cancer (NSCLC) patients and adaptive stereotactic body RT (SBRT) in hepatocellular carcinoma (HCC) patients, respectively. For training and validation, dense data with 297 features were available for 67 NSCLC patients and 110 features for 71 HCC patients. To increase the sample size for ODM training, we applied Generative Adversarial Networks to generate 10,000 synthetic patients. The ODM was trained on the synthetic patients and validated on the original dataset. We found that, Double GNN architecture was able to correct the nonphysical dose-response trend and improve ARCliDS recommendation. The average root mean squared difference (RMSD) between ARCliDS recommendation and reported clinical decisions using double GNNs were 0.61 [0.03] Gy/frac (mean [sem]) for adaptive RT in NSCLC patients and 2.96 [0.42] Gy/frac for adaptive SBRT HCC compared to the single GNN's RMSDs of 0.97 [0.12] Gy/frac and 4.75 [0.16] Gy/frac, respectively. Overall, For NSCLC and HCC, ARCliDS with double GNNs was able to reproduce 36% and 50% of the good clinical decisions (local control and no side effects) and improve 74% and 30% of the bad clinical decisions, respectively. In conclusion, ARCliDS is the first web-based software dedicated to assist KBR-ART with multi-omics data. ARCliDS can learn from the reported clinical decisions and facilitate AI-assisted clinical decision-making for improving the outcomes in DTR.

Machine learning-based colorectal cancer prediction using global dietary data.

BACKGROUND: Colorectal cancer (CRC) is the third most commonly diagnosed cancer worldwide. Active health screening for CRC yielded detection of an increasingly younger adults. However, current machine learning algorithms that are trained using older adults and smaller datasets, may not perform well in practice for large populations. AIM: To evaluate machine learning algorithms using large datasets accounting for both younger and older adults from multiple regions and diverse sociodemographics. METHODS: A large dataset including 109,343 participants in a dietary-based colorectal cancer ase study from Canada, India, Italy, South Korea, Mexico, Sweden, and the United States was collected by the Center for Disease Control and Prevention. This global dietary database was augmented with other publicly accessible information from multiple sources. Nine supervised and unsupervised machine learning algorithms were evaluated on the aggregated dataset. RESULTS: Both supervised and unsupervised models performed well in predicting CRC and non-CRC phenotypes. A prediction model based on an artificial neural network (ANN) was found to be the optimal algorithm with CRC misclassification of 1% and non-CRC misclassification of 3%. CONCLUSIONS: ANN models trained on large heterogeneous datasets may be applicable for both younger and older adults. Such models provide a solid foundation for building effective clinical decision support systems assisting healthcare providers in dietary-related, non-invasive screening that can be applied in large studies. Using optimal algorithms coupled with high compliance to cancer screening is expected to significantly improve early diagnoses and boost the success rate of timely and appropriate cancer interventions.

Sex difference in the associations of socioeconomic status, cognitive function and brain volume with dementia in old adults: Findings from the OASIS study.

Background: Sex differences in the association of cognitive function and imaging measures with dementia have not been fully investigated while sex-based investigation of dementia has been discussed. Understanding sex differences in the dementia-related socioeconomic, cognitive, and imaging measurements is important for uncovering sex-related pathways to dementia and facilitating early diagnosis, family planning, and cost control. Methods: We selected data from the Open Access Series of Imaging Studies with longitudinal measurements of brain volumes on 150 individuals aged 60 to 96 years. Dementia status was determined using the Clinical Dementia Rating (CDR) scale, and Alzheimer's disease was diagnosed as a CDR of ≥ 0.5. Generalized estimating equation models were used to estimate the associations of socioeconomic, cognitive and imaging factors with dementia in men and women. Results: Lower education affected dementia more in women than in men. Age, education, Mini-Mental State Examination (MMSE), and normalized whole-brain volume (nWBV) were associated with dementia in women whereas only MMSE and nWBV were associated with dementia in men. Lower socioeconomic status was associated with a reduced estimated total intracranial volume in men, but not in women. Ageing and lower MMSE scores were associated with reduced nWBV in both men and women. Conclusions: The association between education and prevalence of dementia differs in men and women. Women may have more risk factors for dementia than men.

Brain structure and allelic associations in Alzheimer's disease.

BACKGROUND: Alzheimer's disease (AD), the most prevalent form of dementia, affects 6.5 million Americans and over 50 million people globally. Clinical, genetic, and phenotypic studies of dementia provide some insights of the observed progressive neurodegenerative processes, however, the mechanisms underlying AD onset remain enigmatic. AIMS: This paper examines late-onset dementia-related cognitive impairment utilizing neuroimaging-genetics biomarker associations. MATERIALS AND METHODS: The participants, ages 65-85, included 266 healthy controls (HC), 572 volunteers with mild cognitive impairment (MCI), and 188 Alzheimer's disease (AD) patients. Genotype dosage data for AD-associated single nucleotide polymorphisms (SNPs) were extracted from the imputed ADNI genetics archive using sample-major additive coding. Such 29 SNPs were selected, representing a subset of independent SNPs reported to be highly associated with AD in a recent AD meta-GWAS study by Jansen and colleagues. RESULTS: We identified the significant correlations between the 29 genomic markers (GMs) and the 200 neuroimaging markers (NIMs). The odds ratios and relative risks for AD and MCI (relative to HC) were predicted using multinomial linear models. DISCUSSION: In the HC and MCI cohorts, mainly cortical thickness measures were associated with GMs, whereas the AD cohort exhibited different GM-NIM relations. Network patterns within the HC and AD groups were distinct in cortical thickness, volume, and proportion of White to Gray Matter (pct), but not in the MCI cohort. Multinomial linear models of clinical diagnosis showed precisely the specific NIMs and GMs that were most impactful in discriminating between AD and HC, and between MCI and HC. CONCLUSION: This study suggests that advanced analytics provide mechanisms for exploring the interrelations between morphometric indicators and GMs. The findings may facilitate further clinical investigations of phenotypic associations that support deep systematic understanding of AD pathogenesis.

DataSifterText: Partially Synthetic Text Generation for Sensitive Clinical Notes.

Petabytes of health data are collected annually across the globe in electronic health records (EHR), including significant information stored as unstructured free text. However, the lack of effective mechanisms to securely share clinical text has inhibited its full utilization. We propose a new method, DataSifterText, to generate partially synthetic clinical free-text that can be safely shared between stakeholders (e.g., clinicians, STEM researchers, engineers, analysts, and healthcare providers), limiting the re-identification risk while providing significantly better utility preservation than suppressing or generalizing sensitive tokens. The method creates partially synthetic free-text data, which inherits the joint population distribution of the original data, and disguises the location of true and obfuscated words. Under certain obfuscation levels, the resulting synthetic text was sufficiently altered with different choices, orders, and frequencies of words compared to the original records. The differences were comparable to machine-generated (fully synthetic) text reported in previous studies. We applied DataSifterText to two medical case studies. In the CDC work injury application, using privacy protection, 60.9-86.5% of the synthetic descriptions belong to the same cluster as the original descriptions, demonstrating better utility preservation than the naïve content suppressing method (45.8-85.7%). In the MIMIC III application, the generated synthetic data maintained over 80% of the original information regarding patients' overall health conditions. The reported DataSifterText statistical obfuscation results indicate that the technique provides sufficient privacy protection (low identification risk) while preserving population-level information (high utility).

Transfusion-associated hyperkalemia in pediatric population: Analyses for risk factors and recommendations.

BACKGROUND: Transfusion-associated hyperkalemia (TAH) is a potentially life-threatening complication of red blood cell (RBC) transfusion. Previously, we reported features of RBC transfusions from 35 pediatric patients (TAH group) who had hyperkalemia with RBC transfusion in one-year period at four facilities. In this study, we used multivariate analyses and artificial intelligence to compare the TAH group to newly collected control group (non-TAH group) to identify factors associated with TAH occurrence. STUDY DESIGN: A review of RBC transfusion with TAH was compared to non-TAH group who did not develop TAH with RBC transfusion at each facility during the same one-year period. The non-TAH group included 12 patients each in 5 age groups. Wilcoxon rank-sum tests recursive feature elimination, least absolute shrinkage, and selection operator (LASSO), and other artificial intelligence techniques were employed to identify the most salient features associated with predicting specific clinical outcomes for TAH occurrence. RESULTS/FINDINGS: Pre-transfusion creatinine, comorbidities of kidney and/or liver dysfunctions, and total transfused volume within 12 h (tV-12) per kg and per estimated total blood volume (eTBV) showed statistically significant differences between TAH and non-TAH groups. Multivariate analysis revealed the biggest factor in TAH occurrence was tV-12/kg followed by age of RBC units. The thresholds of risks were tV-12/kg of 30 ml/kg, tV-12/eTBV of 30%, and RBC unit age of 7.95 days. CONCLUSIONS: The study findings suggest that the biggest factor on TAH occurrence is tV-12/kg. More importantly, 30% of eTBV transfusion could cause TAH in patients with multiple comorbidities.

DataSifter II: Partially synthetic data sharing of sensitive information containing time-varying correlated observations.

There is a significant public demand for rapid data-driven scientific investigations using aggregated sensitive information. However, many technical challenges and regulatory policies hinder efficient data sharing. In this study, we describe a partially synthetic data generation technique for creating anonymized data archives whose joint distributions closely resemble those of the original (sensitive) data. Specifically, we introduce the DataSifter technique for time-varying correlated data (DataSifter II), which relies on an iterative model-based imputation using generalized linear mixed model and random effects-expectation maximization tree. DataSifter II can be used to generate synthetic repeated measures data for testing and validating new analytical techniques. Compared to the multiple imputation method, DataSifter II application on simulated and real clinical data demonstrates that the new method provides extensive reduction of re-identification risk (data privacy) while preserving the analytical value (data utility) in the obfuscated data. The performance of the DataSifter II on a simulation involving 20% artificially missingness in the data, shows at least 80% reduction of the disclosure risk, compared to the multiple imputation method, without a substantial impact on the data analytical value. In a separate clinical data (Medical Information Mart for Intensive Care III) validation, a model-based statistical inference drawn from the original data agrees with an analogous analytical inference obtained using the DataSifter II obfuscated (sifted) data. For large time-varying datasets containing sensitive information, the proposed technique provides an automated tool for alleviating the barriers of data sharing and facilitating effective, advanced, and collaborative analytics.

The clusters of health-risk behaviours and mental wellbeing and their sociodemographic correlates: a study of 15,366 ASEAN university students.

BACKGROUND: This study investigated, through cluster analysis, the associations between behavioural characteristics, mental wellbeing, demographic characteristics, and health among university students in the Association of Southeast Asian Nations (ASEAN) University Network - Health Promotion Network (AUN-HPN) member universities. METHODS: Data were retrieved from a cross-sectional self-administered online survey among undergraduate students in seven ASEAN countries. A two-step cluster analysis was employed, with cluster labels based on the predominant characteristics identified within the clusters. The 'healthy' cluster was assigned as the reference group for comparisons using multinomial logistic regression analysis. RESULTS: The analytic sample size comprised 15,366 university students. Five clusters of student-types were identified: (i) 'Healthy' (n = 1957; 12.7%); (ii) 'High sugary beverage consumption' (n = 8482; 55.2%); (iii) 'Poor mental wellbeing' (n = 2009; 13.1%); (iv) 'Smoker' (n = 1364; 8.9%); and (v) 'Alcohol drinker' (n = 1554; 10.1%). Being female (OR 1.28, 95%CI 1.14, 1.45) and being physically inactive (OR 1.20, 95%CI 1.04, 1.39) increased the odds of belonging to the 'High sugary beverage consumption' cluster. Being female (OR 1.21, 95%CI 1.04, 1.41), non-membership in a sports club (OR 1.83, 95%CI 1.43, 2.34) were associated with 'Poor mental wellbeing'. Obesity (OR 2.03, 95%CI 1.47, 2.80), inactively commuting to campus (OR 1.34, 95%CI 1.09, 1.66), and living in high-rise accommodation (OR 2.94, 95%CI 1.07, 8.07) were associated with membership in the 'Smoker' cluster. Students living in The Philippines, Singapore, Thailand, and Vietnam had a higher likelihood of being alcohol drinkers, compared with those who lived in Brunei. CONCLUSIONS: ASEAN university students exhibited health-risk behaviours that typically clustered around a specific health behaviour and mental wellbeing. The results provided support for focusing interventions on one dominant health-risk behaviour, with associated health-risk behaviours within clusters being potential mediators for consideration.

Determinism, well-posedness, and applications of the ultrahyperbolic wave equation in spacekime.

Spatiotemporal dynamics of many natural processes, such as elasticity, heat propagation, sound waves, and fluid flows are often modeled using partial differential equations (PDEs). Certain types of PDEs have closed-form analytical solutions, some permit only numerical solutions, some require appropriate initial and boundary conditions, and others may not have stable, global, or even well-posed solutions. In this paper, we focus on one-specific type of second-order PDE - the ultrahyperbolic wave equation in multiple time dimensions. We demonstrate the wave equation solutions in complex time (kime) and show examples of the Cauchy initial value problem in space-kime. We extend the classical formulation of the dynamics of the wave equation with respect to positive real longitudinal time. The solutions to the Cauchy boundary value problem in multiple time dimensions are derived in Cartesian, polar, and spherical coordinates. These include both bounded and unbounded spatial domains. Some example solutions are shown in the main text with additional web-based dynamic illustrations of the wave equation solutions in space-kime shown in the appendix. Solving PDEs in complex time has direct connections to data science, where solving under-determined linear modeling problems or specifying the initial conditions on limited spatial dimensions may be insufficient to forecast, classify, or predict a prospective value of a parameter or a statistical model. This approach extends the notion of data observations, anchored at ordered longitudinal events, to complex time, where observables need not follow a strict positive-real structural arrangement, but instead could traverse the entire kime plane.

Kimesurface Representation and Tensor Linear Modeling of Longitudinal Data.

Many modern techniques for analyzing time-varying longitudinal data rely on parametric models to interrogate the time-courses of univariate or multivariate processes. Typical analytic objectives include utilizing retrospective observations to model current trends, predict prospective trajectories, derive categorical traits, or characterize various relations. Among the many mathematical, statistical, and computational strategies for analyzing longitudinal data, tensor-based linear modeling offers a unique algebraic approach that encodes different characterizations of the observed measurements in terms of state indices. This paper introduces a new method of representing, modeling, and analyzing repeated-measurement longitudinal data using a generalization of event order from the positive reals to the complex plane. Using complex time (kime), we transform classical time-varying signals as 2D manifolds called kimesurfaces. This kime characterization extends the classical protocols for analyzing time-series data and offers unique opportunities to design novel inference, prediction, classification, and regression techniques based on the corresponding kimesurface manifolds. We define complex time and illustrate alternative time-series to kimesurface transformations. Using the Laplace transform and its inverse, we demonstrate the bijective mapping between time-series and kimesurfaces. A proposed general tensor regression based linear model is validated using functional Magnetic Resonance Imaging (fMRI) data. This kimesurface representation method can be used with a wide range of machine learning algorithms, artificial intelligence tools, analytical approaches, and inferential techniques to interrogate multivariate, complex-domain, and complex-range longitudinal processes.

Znet: Deep Learning Approach for 2D MRI Brain Tumor Segmentation.

BACKGROUND: Detection and segmentation of brain tumors using MR images are challenging and valuable tasks in the medical field. Early diagnosing and localizing of brain tumors can save lives and provide timely options for physicians to select efficient treatment plans. Deep learning approaches have attracted researchers in medical imaging due to their capacity, performance, and potential to assist in accurate diagnosis, prognosis, and medical treatment technologies. METHODS AND PROCEDURES: This paper presents a novel framework for segmenting 2D brain tumors in MR images using deep neural networks (DNN) and utilizing data augmentation strategies. The proposed approach (Znet) is based on the idea of skip-connection, encoder-decoder architectures, and data amplification to propagate the intrinsic affinities of a relatively smaller number of expert delineated tumors, e.g., hundreds of patients of the low-grade glioma (LGG), to many thousands of synthetic cases. RESULTS: Our experimental results showed high values of the mean dice similarity coefficient (dice = 0.96 during model training and dice = 0.92 for the independent testing dataset). Other evaluation measures were also relatively high, e.g., pixel accuracy = 0.996, F1 score = 0.81, and Matthews Correlation Coefficient, MCC = 0.81. The results and visualization of the DNN-derived tumor masks in the testing dataset showcase the ZNet model's capability to localize and auto-segment brain tumors in MR images. This approach can further be generalized to 3D brain volumes, other pathologies, and a wide range of image modalities. CONCLUSION: We can confirm the ability of deep learning methods and the proposed Znet framework to detect and segment tumors in MR images. Furthermore, pixel accuracy evaluation may not be a suitable evaluation measure for semantic segmentation in case of class imbalance in MR images segmentation. This is because the dominant class in ground truth images is the background. Therefore, a high value of pixel accuracy can be misleading in some computer vision applications. On the other hand, alternative evaluation metrics, such as dice and IoU (Intersection over Union), are more factual for semantic segmentation. CLINICAL IMPACT: Artificial intelligence (AI) applications in medicine are advancing swiftly, however, there is a lack of deployed techniques in clinical practice. This research demonstrates a practical example of AI applications in medical imaging, which can be deployed as a tool for auto-segmentation of tumors in MR images.

Precision radiotherapy via information integration of expert human knowledge and AI recommendation to optimize clinical decision making.

In the precision medicine era, there is a growing need for precision radiotherapy where the planned radiation dose needs to be optimally determined by considering a myriad of patient-specific information in order to ensure treatment efficacy. Existing artificial-intelligence (AI) methods can recommend radiation dose prescriptions within the scope of this available information. However, treating physicians may not fully entrust the AI's recommended prescriptions due to known limitations or at instances when the AI recommendation may go beyond physicians' current knowledge. This paper lays out a systematic method to integrate expert human knowledge with AI recommendations for optimizing clinical decision making. Towards this goal, Gaussian process (GP) models are integrated with deep neural networks (DNNs) to quantify the uncertainty of the treatment outcomes given by physicians and AI recommendations, respectively, which are further used as a guideline to educate clinical physicians and improve AI models performance. The proposed method is demonstrated in a comprehensive dataset where patient-specific information and treatment outcomes are prospectively collected during radiotherapy of 67 non-small cell lung cancer (NSCLC) patients and are retrospectively analyzed.

Optimal dynamic treatment regime estimation using information extraction from unstructured clinical text.

The wide-scale adoption of electronic health records (EHRs) provides extensive information to support precision medicine and personalized health care. In addition to structured EHRs, we leverage free-text clinical information extraction (IE) techniques to estimate optimal dynamic treatment regimes (DTRs), a sequence of decision rules that dictate how to individualize treatments to patients based on treatment and covariate history. The proposed IE of patient characteristics closely resembles "The clinical Text Analysis and Knowledge Extraction System" and employs named entity recognition, boundary detection, and negation annotation. It also utilizes regular expressions to extract numerical information. Combining the proposed IE with optimal DTR estimation, we extract derived patient characteristics and use tree-based reinforcement learning (T-RL) to estimate multistage optimal DTRs. IE significantly improved the estimation in counterfactual outcome models compared to using structured EHR data alone, which often include incomplete data, data entry errors, and other potentially unobserved risk factors. Moreover, including IE in optimal DTR estimation provides larger study cohorts and a broader pool of candidate tailoring variables. We demonstrate the performance of our proposed method via simulations and an application using clinical records to guide blood pressure control treatments among critically ill patients with severe acute hypertension. This joint estimation approach improves the accuracy of identifying the optimal treatment sequence by 14-24% compared to traditional inference without using IE, based on our simulations over various scenarios. In the blood pressure control application, we successfully extracted significant blood pressure predictors that are unobserved or partially missing from structured EHR.

Prediction Modeling of Mental Well-Being Using Health Behavior Data of College Students.

Background: Since the onset of the COVID-19 pandemic in early 2020, the importance of timely and effective assessment of mental well-being has increased dramatically. Due to heightened risks for developing mental illness, this trend is likely to continue during the post-pandemic period. Machine learning (ML) algorithms and artificial intelligence (AI) techniques can be harnessed for early detection, prognostication and prediction of negative psychological well-being states. Objective: Studies using machine learning classification of mental well-being are scarce in Asian populations. This investigation aims to develop reliable machine learning classifiers based on health behavior indicators applicable to university students in South-East Asia. Methods: Using data from a large, multi-site cross-sectional survey, this research work models mental well-being and reports on the performance of various machine learning algorithms, such as generalized linear models, k-nearest neighbor, naïve-Bayes, neural networks, random forest, recursive partitioning, bagging, and boosting. Prediction models were evaluated using various metrics such as accuracy, error rate, kappa, sensitivity, specificity, Area Under the recursive operating characteristic Curve (AUC), and Gini Index. Results: Random forest and adaptive boosting algorithms achieved the highest accuracy of identifying negative mental well-being traits. The top five most salient features associated with predicting poor mental well-being include body mass index, number of sports activities per week, grade point average (GPA), sedentary hours, and age. Conclusions: Based on the reported results, several specific recommendations and suggested future work are discussed. These findings may be useful to provide cost-effective support and modernize mental well-being assessment and monitoring at the individual and university level.

Interactive Visualization and Computation of 2D and 3D Probability Distributions.

Purpose: Mathematical modeling, probability estimation, and statistical inference represent core elements of modern artificial intelligence (AI) approaches for data-driven prediction, forecasting, classification, risk-estimation, and prognosis. Currently there are many tools that help calculate and visualize univariate probability distributions, however, very few resources venture beyond into multivariate distributions, which are commonly used in advanced statistical inference and AI decision-making. This article presents a new web-calculator that enables some calculation and visualization of bivariate and trivariate probability distributions. Methods: Several methods are explored to compute the joint bivariate and trivariate probability densities, including the optimal multivariate modeling using Gaussian copula. We developed an interactive webapp to visually illustrate the parallels between the mathematical formulation, computational implementation, and graphical depiction of multivariate probability density and cumulative distribution functions. To ensure the interface and functionality are hardware platform independent, scalable, and functional, the app and its component widgets are implemented using HTML5 and JavaScript. Results: We validated the webapp by testing the multivariate copula models under different experimental conditions and inspecting the performance in terms of accuracy and reliability of the estimated multivariate probability densities and distribution function values. Conclusion: This article demonstrates the construction, implementation, and utilization of multivariate probability calculators. The proposed webapp implementation is freely available online (https://socr.umich.edu/HTML5/BivariateNormal/BVN2/) and can be used to assist with education and research of a diverse array of data scientists, STEM instructors, and AI learners.