Machine Learning Models for Pancreatic Cancer Risk Prediction Using Electronic Health Record Data-A Systematic Review and Assessment.

INTRODUCTION: Accurate risk prediction can facilitate screening and early detection of pancreatic cancer (PC). We conducted a systematic review to critically evaluate effectiveness of machine learning (ML) and artificial intelligence (AI) techniques applied to electronic health records (EHR) for PC risk prediction. METHODS: Ovid MEDLINE(R), Ovid EMBASE, Ovid Cochrane Central Register of Controlled Trials, Ovid Cochrane Database of Systematic Reviews, Scopus, and Web of Science were searched for articles that utilized ML/AI techniques to predict PC, published between January 1, 2012, and February 1, 2024. Study selection and data extraction were conducted by 2 independent reviewers. Critical appraisal and data extraction were performed using the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies checklist. Risk of bias and applicability were examined using prediction model risk of bias assessment tool. RESULTS: Thirty studies including 169,149 PC cases were identified. Logistic regression was the most frequent modeling method. Twenty studies utilized a curated set of known PC risk predictors or those identified by clinical experts. ML model discrimination performance (C-index) ranged from 0.57 to 1.0. Missing data were underreported, and most studies did not implement explainable-AI techniques or report exclusion time intervals. DISCUSSION: AI/ML models for PC risk prediction using known risk factors perform reasonably well and may have near-term applications in identifying cohorts for targeted PC screening if validated in real-world data sets. The combined use of structured and unstructured EHR data using emerging AI models while incorporating explainable-AI techniques has the potential to identify novel PC risk factors, and this approach merits further study.

Identification of pancreatic cancer risk factors from clinical notes using natural language processing.

OBJECTIVES: Screening for pancreatic ductal adenocarcinoma (PDAC) is considered in high-risk individuals (HRIs) with established PDAC risk factors, such as family history and germline mutations in PDAC susceptibility genes. Accurate assessment of risk factor status is provider knowledge-dependent and requires extensive manual chart review by experts. Natural Language Processing (NLP) has shown promise in automated data extraction from the electronic health record (EHR). We aimed to use NLP for automated extraction of PDAC risk factors from unstructured clinical notes in the EHR. METHODS: We first developed rule-based NLP algorithms to extract PDAC risk factors at the document-level, using an annotated corpus of 2091 clinical notes. Next, we further improved the NLP algorithms using a cohort of 1138 patients through patient-level training, validation, and testing, with comparison against a pre-specified reference standard. To minimize false-negative results we prioritized algorithm recall. RESULTS: In the test set (n = 807), the NLP algorithms achieved a recall of 0.933, precision of 0.790, and F1-score of 0.856 for family history of PDAC. For germline genetic mutations, the algorithm had a high recall of 0.851, while precision and F1-score were lower at 0.350 and 0.496 respectively. Most false positives for germline mutations resulted from erroneous recognition of tissue mutations. CONCLUSIONS: Rule-based NLP algorithms applied to unstructured clinical notes are highly sensitive for automated identification of PDAC risk factors. Further validation in a large primary-care patient population is warranted to assess real-world utility in identifying HRIs for pancreatic cancer screening.

DNA polymerase gamma mutations that impair holoenzyme stability cause catalytic subunit depletion.

Mutations in POLG, encoding POLγA, the catalytic subunit of the mitochondrial DNA polymerase, cause a spectrum of disorders characterized by mtDNA instability. However, the molecular pathogenesis of POLG-related diseases is poorly understood and efficient treatments are missing. Here, we generate the PolgA449T/A449T mouse model, which reproduces the A467T change, the most common human recessive mutation of POLG. We show that the mouse A449T mutation impairs DNA binding and mtDNA synthesis activities of POLγ, leading to a stalling phenotype. Most importantly, the A449T mutation also strongly impairs interactions with POLγB, the accessory subunit of the POLγ holoenzyme. This allows the free POLγA to become a substrate for LONP1 protease degradation, leading to dramatically reduced levels of POLγA in A449T mouse tissues. Therefore, in addition to its role as a processivity factor, POLγB acts to stabilize POLγA and to prevent LONP1-dependent degradation. Notably, we validated this mechanism for other disease-associated mutations affecting the interaction between the two POLγ subunits. We suggest that targeting POLγA turnover can be exploited as a target for the development of future therapies.

Machine Learning-Based Classification of Abnormal Liver Tissues Using Relative Permittivity.

The search for non-invasive, fast, and low-cost diagnostic tools has gained significant traction among many researchers worldwide. Dielectric properties calculated from microwave signals offer unique insights into biological tissue. Material properties, such as relative permittivity (εr) and conductivity (σ), can vary significantly between healthy and unhealthy tissue types at a given frequency. Understanding this difference in properties is key for identifying the disease state. The frequency-dependent nature of the dielectric measurements results in large datasets, which can be postprocessed using artificial intelligence (AI) methods. In this work, the dielectric properties of liver tissues in three mouse models of liver disease are characterized using dielectric spectroscopy. The measurements are grouped into four categories based on the diets or disease state of the mice, i.e., healthy mice, mice with non-alcoholic steatohepatitis (NASH) induced by choline-deficient high-fat diet, mice with NASH induced by western diet, and mice with liver fibrosis. Multi-class classification machine learning (ML) models are then explored to differentiate the liver tissue groups based on dielectric measurements. The results show that the support vector machine (SVM) model was able to differentiate the tissue groups with an accuracy up to 90%. This technology pipeline, thus, shows great potential for developing the next generation non-invasive diagnostic tools.

Human Cytomegalovirus miR-UL70-3p Downregulates the H2O2-Induced Apoptosis by Targeting the Modulator of Apoptosis-1 (MOAP1).

Human Cytomegalovirus (HCMV) is a prototypic beta herpesvirus, causing persistent infections in humans. There are medications that are used to treat the symptoms; however, there is no cure yet. Thus, understanding the molecular mechanisms of HCMV replication and its persistence may reveal new prevention strategies. HCMV evasive strategies on the antiviral responses of the human host largely rely on its significant portion of genome. Numerous studies have highlighted the importance of miRNA-mediated regulation of apoptosis, which is an innate immune mechanism that eradicates virus-infected cells. In this study, we explore the antiapoptotic role of hcmv-miR-UL70-3p in HEK293T cells. We establish that hcmv-miR-UL70-3p targets the proapoptotic gene Modulator of Apoptosis-1 (MOAP1) through interaction with its 3'UTR region of mRNA. The ectopic expression of hcmv-miR-UL70-3p mimic significantly downregulates the H2O2-induced apoptosis through the translational repression of MOAP1. Silencing of MOAP1 through siRNA also inhibits the H2O2-induced apoptosis, which further supports the hcmv-miR-UL70-3p mediated antiapoptotic effect by regulating MOAP1 expression. These results uncover a role for hcmv-miR-UL70-3p and its target MOAP1 in regulating apoptosis.

Tracking personalized functional health in older adults using geriatric assessments.

BACKGROUND: Higher levels of functional health in older adults leads to higher quality of life and improves the ability to age-in-place. Tracking functional health objectively could help clinicians to make decisions for interventions in case of health deterioration. Even though several geriatric assessments capture several aspects of functional health, there is limited research in longitudinally tracking personalized functional health of older adults using a combination of these assessments. METHODS: We used geriatric assessment data collected from 150 older adults to develop and validate a functional health prediction model based on risks associated with falls, hospitalizations, emergency visits, and death. We used mixed effects logistic regression to construct the model. The geriatric assessments included were Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), Mini-Mental State Examination (MMSE), Geriatric Depression Scale (GDS), and Short Form 12 (SF12). Construct validators such as fall risks associated with model predictions, and case studies with functional health trajectories were used to validate the model. RESULTS: The model is shown to separate samples with and without adverse health event outcomes with an area under the receiver operating characteristic curve (AUC) of > 0.85. The model could predict emergency visit or hospitalization with an AUC of 0.72 (95% CI 0.65-0.79), fall with an AUC of 0.86 (95% CI 0.83-0.89), fall with hospitalization with an AUC of 0.89 (95% CI 0.85-0.92), and mortality with an AUC of 0.93 (95% CI 0.88-0.97). Multiple comparisons of means using Turkey HSD test show that model prediction means for samples with no adverse health events versus samples with fall, hospitalization, and death were statistically significant (p < 0.001). Case studies for individual residents using predicted functional health trajectories show that changes in model predictions over time correspond to critical health changes in older adults. CONCLUSIONS: The personalized functional health tracking may provide clinicians with a longitudinal view of overall functional health in older adults to help address the early detection of deterioration trends and decide appropriate interventions. It can also help older adults and family members take proactive steps to improve functional health.

FANCJ helicase controls the balance between short- and long-tract gene conversions between sister chromatids.

The FANCJ DNA helicase is linked to hereditary breast and ovarian cancers as well as bone marrow failure disorder Fanconi anemia (FA). Although FANCJ has been implicated in the repair of DNA double-strand breaks (DSBs) by homologous recombination (HR), the molecular mechanism underlying the tumor suppressor functions of FANCJ remains obscure. Here, we demonstrate that FANCJ deficient human and hamster cells exhibit reduction in the overall gene conversions in response to a site-specific chromosomal DSB induced by I-SceI endonuclease. Strikingly, the gene conversion events were biased in favour of long-tract gene conversions in FANCJ depleted cells. The fine regulation of short- (STGC) and long-tract gene conversions (LTGC) by FANCJ was dependent on its interaction with BRCA1 tumor suppressor. Notably, helicase activity of FANCJ was essential for controlling the overall HR and in terminating the extended repair synthesis during sister chromatid recombination (SCR). Moreover, cells expressing FANCJ pathological mutants exhibited defective SCR with an increased frequency of LTGC. These data unravel the novel function of FANCJ helicase in regulating SCR and SCR associated gene amplification/duplications and imply that these functions of FANCJ are crucial for the genome maintenance and tumor suppression.

Mammalian RAD51 paralogs protect nascent DNA at stalled forks and mediate replication restart.

Mammalian RAD51 paralogs are implicated in the repair of collapsed replication forks by homologous recombination. However, their physiological roles in replication fork maintenance prior to fork collapse remain obscure. Here, we report on the role of RAD51 paralogs in short-term replicative stress devoid of DSBs. We show that RAD51 paralogs localize to nascent DNA and common fragile sites upon replication fork stalling. Strikingly, RAD51 paralogs deficient cells exhibit elevated levels of 53BP1 nuclear bodies and increased DSB formation, the latter being attributed to extensive degradation of nascent DNA at stalled forks. RAD51C and XRCC3 promote the restart of stalled replication in an ATP hydrolysis dependent manner by disengaging RAD51 and other RAD51 paralogs from the halted forks. Notably, we find that Fanconi anemia (FA)-like disorder and breast and ovarian cancer patient derived mutations of RAD51C fails to protect replication fork, exhibit under-replicated genomic regions and elevated micro-nucleation. Taken together, RAD51 paralogs prevent degradation of stalled forks and promote the restart of halted replication to avoid replication fork collapse, thereby maintaining genomic integrity and suppressing tumorigenesis.

Enhanced non-homologous end joining contributes toward synthetic lethality of pathological RAD51C mutants with poly (ADP-ribose) polymerase.

Poly (ADP-ribose) polymerase 1 (PARP1) inhibitors are actively under clinical trials for the treatment of breast and ovarian cancers that arise due to mutations in BRCA1 and BRCA2. The RAD51 paralog RAD51C has been identified as a breast and ovarian cancer susceptibility gene. The pathological RAD51C mutants that were identified in cancer patients are hypomorphic with partial repair function. However, targeting cancer cells that express hypomorphic mutants of RAD51C is highly challenging. Here, we report that RAD51C-deficient cells can be targeted by a 'synthetic lethal' approach using PARP inhibitor and this sensitivity was attributed to accumulation of cells in the G2/M and chromosomal aberrations. In addition, spontaneous hyperactivation of PARP1 was evident in RAD51C-deficient cells. Interestingly, RAD51C-negative cells exhibited enhanced recruitment of non-homologous end joining (NHEJ) proteins onto chromatin and this accumulation correlated with increased activity of error-prone NHEJ as well as genome instability leading to cell death. Notably, inhibition of DNA-PKcs or depletion of KU70 or Ligase IV rescued this phenotype. Strikingly, stimulation of NHEJ by low dose of ionizing radiation (IR) in the PARP inhibitor-treated RAD51C-deficient cells and cells expressing pathological RAD51C mutants induced enhanced toxicity 'synergistically'. These results demonstrate that cancer cells arising due to hypomorphic mutations in RAD51C can be specifically targeted by a 'synergistic approach' and imply that this strategy can be potentially applied to cancers with hypomorphic mutations in other homologous recombination pathway genes.

Estimating the Effect of Genital vs Extragenital Warts on Immunocompetent Indian Adult Patients; Quality of Life: A Comparative Cross-Sectional Study.

Introduction: Extragenital warts, often known as EGWs, affect between 7% and 10% of the population. Despite the plethora of research on the impact of genital warts (GWs) on "Quality Of Life", EGWs have received little attention. The purpose of this study was to conduct a cross-sectional investigation with the objective of contrasting the effects of GWs and EGWs on the health-related quality of life and other characteristics. Participants and Procedures: A cross-sectional clinical study was piloted at a tertiary care center. Participants in the study included two groups of healthy adults, each group consisting of 100 adult subjects. Those diagnosed with EGWs were included in group A, while patients diagnosed with GWs made up group B. The "Dermatology Life Quality Index" questionnaire was used to evaluate various parameters. Observations were compared for significance. Results: The majority of the subjects in both the groups were observed to have less than 10 warts. The Dermatology Life Quality Index score for the EGWs had an average of 8.66 ± 2.31 score; GWs had an average of 5.12 ± 3.25. This mean variance was statistically significant. The level of the dissatisfaction was highly significantly different among the groups and the subjects being more in the EGW group dissatisfied. Conclusion: The findings of this investigation indicate that EGWs have a significant and detrimental effect on the Quality Of Life. Medical experts must teach people how to prevent the disease's spread and recurrence due to its persistence. They must also consider the psychological and societal repercussions of the disease while discussing therapy choices.

Fall Risk Prediction in Older Adults Using Free-Text Nursing Notes and Medications in Electronic Health Records.

Nursing notes in Electronic Health Records (EHR) contain critical health information, including fall risk factors. However, an exploration of fall risk prediction using nursing notes is not well examined. In this study, we explored deep learning architectures to predict fall risk in older adults using text in nursing notes and medications in the EHR. EHR predictor data and fall events outcome data were obtained from 162 older adults living at TigerPlace, a senior living facility located in Columbia, MO. We used pre-trained BioWordVec embeddings to represent the words in the clinical notes and medications and trained multiple recurrent neural network-based natural language processing models to predict future fall events. Our final model predicted falls with an accuracy of 0.81, a sensitivity of 0.75, a specificity of 0.83, and an F1 score of 0.82. This preliminary exploratory analysis provides supporting evidence that fall risk can be predicted from clinical notes and medications. Future studies will utilize additional data modalities available in the EHR to potentially improve fall risk prediction from EHR data.

Explainable Fall Risk Prediction in Older Adults Using Gait and Geriatric Assessments.

Older adults aged 65 and above are at higher risk of falls. Predicting fall risk early can provide caregivers time to provide interventions, which could reduce the risk, potentially avoiding a possible fall. In this paper, we present an analysis of 6-month fall risk prediction in older adults using geriatric assessments, GAITRite measurements, and fall history. The geriatric assessments included were Activities of Daily Living (ADL), Instrumental Activities of Daily Living (IADL), Mini-Mental State Examination (MMSE), Geriatric Depression Scale (GDS), and Short Form 12 (SF12). These geriatric assessments are collected by staff nurses regularly in senior care facilities. From the GAITRite assessments on the residents, we included the Functional Ambulatory Profile (FAP) scores and gait speed to predict fall risk. We used the SHAP (SHapley Additive exPlanations) approach to explain our model predictions to understand which predictor variables contributed to increase or decrease the fall risk for an individual prediction. In case of a high fall risk prediction, predictor variables that contributed the most to elevate the risk could be further examined by the health providers for more personalized health interventions. We used the geriatric assessments, GAITRite measurements, and fall history data collected from 92 older adult residents (age = 86.2 ± 6.4, female = 57) to train machine learning models to predict 6-month fall risk. Our models predicted a 6-month fall with an AUC of 0.80 (95% CI of 0.76-0.85), sensitivity of 0.82 (95% CI of 0.74-0.89), specificity of 0.72 (95% CI of 0.67-0.76), F1 score of 0.76 (95% CI of 0.72-0.79), and accuracy of 0.75 (95% CI of 0.72-0.79). These results show that our early fall risk prediction method performs well in identifying residents who are at higher fall risk, which offers care providers and family members valuable time to perform preventive actions.

Disease causing mutation (P178L) in mitochondrial transcription factor A results in impaired mitochondrial transcription initiation.

Mitochondrial transcription factor A (TFAM) is essential for the maintenance, expression, and packaging of mitochondrial DNA (mtDNA). Recently, a pathogenic homozygous variant in TFAM (P178L) has been associated with a severe mtDNA depletion syndrome leading to neonatal liver failure and early death. We have performed a biochemical characterization of the TFAM variant P178L in order to understand the molecular basis for the pathogenicity of this mutation. We observe no effects on DNA binding, and compaction of DNA is only mildly affected by the P178L amino acid change. Instead, the mutation severely impairs mtDNA transcription initiation at the mitochondrial heavy and light strand promoters. Molecular modeling suggests that the P178L mutation affects promoter sequence recognition and the interaction between TFAM and the tether helix of POLRMT, thus explaining transcription initiation deficiency.

Efficacy of Spironolactone in Adult Acne in Polycystic Ovary Syndrome Patients an Original Research.

INTRODUCTION: This prospective clinical trial was designed to assess the effects of a long-term therapy with spironolactone, with and without dietary-induced weight-loss, on clinical features, lipid profile, and insulin levels in women with polycystic ovary syndrome (PCOS). MATERIALS AND METHODS: Twenty-five patients (range of age 16-32 year; 13 lean and 12 overweight) fulfilling formal diagnostic criteria for PCOS (oligomenorrhea and/or amenorrhea, biochemical and/or clinical evidence of hyperadrogenism) were studied at baseline and then received oral spironolactone (100 mg/die) for 12 months; association with lifestyle modifications was recommended to all overweight patients. Clinical, endocrine, and metabolic parameters (oral glucose tolerance test [OGTT], lipid profile) were measured at baseline and at the end of the antiandrogen treatment. RESULTS: The therapy was associated with a significant average decline of triglycerides in overweight subjects and with increased high-density lipoprotein-cholesterol levels in lean patients. The insulin levels at 60 min during OGTT, homeostasis model assessment-insulin resistance and area under curve of insulin were significantly lowered in overweight women after 12 months of spironolactone and weight loss and no negative changes in insulin secretion and sensitivity were observed in PCOS women after pharmacological treatment alone. CONCLUSION: The efficacy of spironolactone on the androgenic clinical aspects of PCOS has been confirmed in this study. Furthermore, our data show that long-term treatment with spironolactone exerts no negative effects on lipoprotein profile and glucose metabolism; more relevant beneficial effects on glucose and lipid metabolism were observed when the antiandrogen was associated with weight loss in overweight PCOS women.

RAD51C/XRCC3 Facilitates Mitochondrial DNA Replication and Maintains Integrity of the Mitochondrial Genome.

Mechanisms underlying mitochondrial genome maintenance have recently gained wide attention, as mutations in mitochondrial DNA (mtDNA) lead to inherited muscular and neurological diseases, which are linked to aging and cancer. It was previously reported that human RAD51, RAD51C, and XRCC3 localize to mitochondria upon oxidative stress and are required for the maintenance of mtDNA stability. Since RAD51 and RAD51 paralogs are spontaneously imported into mitochondria, their precise role in mtDNA maintenance under unperturbed conditions remains elusive. Here, we show that RAD51C/XRCC3 is an additional component of the mitochondrial nucleoid having nucleus-independent roles in mtDNA maintenance. RAD51C/XRCC3 localizes to the mtDNA regulatory regions in the D-loop along with the mitochondrial polymerase POLG, and this recruitment is dependent upon Twinkle helicase. Moreover, upon replication stress, RAD51C and XRCC3 are further enriched at the mtDNA mutation hot spot region D310. Notably, the absence of RAD51C/XRCC3 affects the stability of POLG on mtDNA. As a consequence, RAD51C/XRCC3-deficient cells exhibit reduced mtDNA synthesis and increased lesions in the mitochondrial genome, leading to overall unhealthy mitochondria. Together, these findings lead to the proposal of a mechanism for a direct role of RAD51C/XRCC3 in maintaining mtDNA integrity under replication stress conditions.

Evaluation of the microsoft kinect skeletal versus depth data analysis for timed-up and go and figure of 8 walk tests.

We compared the performance of the Kinect skeletal data with the Kinect depth data in capturing different gait parameters during the Timed-up and Go Test (TUG) and Figure of 8 Walk Test (F8W). The gait parameters considered were stride length, stride time, and walking speed for the TUG, and number of steps and completion time for the F8W. A marker-based Vicon motion capture system was used for the ground-truth measurements. Five healthy participants were recruited for the experiment and were asked to perform three trials of each task. Results show that depth data analysis yields stride length and stride time measures with significantly low percentile errors as compared to the skeletal data analysis. However, the skeletal and depth data performed similar with less than 3% of absolute mean percentile error in determining the walking speed for the TUG and both parameters of F8W. The results show potential capabilities of Kinect depth data analysis in computing many gait parameters, whereas, the Kinect skeletal data can also be used for walking speed in TUG and F8W gait parameters.

Development and preliminary validation of an interactive remote physical therapy system.

In this paper, we present an interactive physical therapy system (IPTS) for remote quantitative assessment of clients in the home. The system consists of two different interactive interfaces connected through a network, for a real-time low latency video conference using audio, video, skeletal, and depth data streams from a Microsoft Kinect. To test the potential of IPTS, experiments were conducted with 5 independent living senior subjects in Kansas City, MO. Also, experiments were conducted in the lab to validate the real-time biomechanical measures calculated using the skeletal data from the Microsoft Xbox 360 Kinect and Microsoft Xbox One Kinect, with ground truth data from a Vicon motion capture system. Good agreements were found in the validation tests. The results show potential capabilities of the IPTS system to provide remote physical therapy to clients, especially older adults, who may find it difficult to visit the clinic.

Follicular psoriasis causing erythroderma in a child: A rare presentation.

Erythroderma in children is an uncommon, yet striking entity with an incidence of 0.11%. Psoriatic erythroderma accounts for 1.4% of psoriasis cases in children. Follicular psoriasis is an underdiagnosed variant of psoriasis, with only about 15 cases reported till date, characterized by scaly follicular papules on the trunk and extremities. Although two thirds of these reported occurred in adults, cases have been described in children under the age of 10 years. Follicular lesions may present without psoriasis vulgaris elsewhere. We report here a 13-year-old boy who presented with severe erythrodermic psoriasis that started as dark, rough, horny, discrete, follicular papules over knees and elbows, associated with nail and joint involvement. Such a presentation of follicular psoriasis causing erythroderma is uncommonly seen in children and has not yet been reported in literature.