Efficient, specific, and combinatorial control of endogenous exon splicing with dCasRx-RBM25.

Efficient targeted control of splicing is a major goal of functional genomics and therapeutic applications. Guide (g)RNA-directed, deactivated (d)Cas CRISPR enzymes fused to splicing effectors represent a promising strategy due to the flexibility of these systems. However, efficient, specific, and generalizable activation of endogenous exons using this approach has not been previously reported. By screening over 300 dCasRx-splicing factor fusion proteins tethered to splicing reporters, we identify dCasRx-RBM25 as a potent activator of exons. Moreover, dCasRx-RBM25 efficiently activates the splicing of ∼90% of targeted endogenous alternative exons and displays high on-target specificity. Using gRNA arrays for combinatorial targeting, we demonstrate that dCasRx-RBM25 enables multiplexed activation and repression of exons. Using this feature, the targeting of neural-regulated exons in Ptpb1 and Puf60 in embryonic stem cells reveals combinatorial effects on downstream alternative splicing events controlled by these factors. Collectively, our results enable versatile, combinatorial exon-resolution functional assays and splicing-directed therapeutic applications.

Implementation of a Blended-Learning Perioperative Nursing Education Program in Canada.

Governmental COVID-19 mandates in Ontario, Canada, resulted in a backlog of perioperative procedures. Organization leaders were required to expand services after the pandemic; however, the ongoing nursing shortage and college-based structure of perioperative education programs complicated their response. In 2021, we developed an in-house perioperative education program using a blended-learning theory comprising online modules and videos, skills laboratory sessions, and clinical placement experiences. Nurses were required to apply for the program and remain employed at the facility for two years. Program evaluations showed that the novice nurses felt confident when beginning clinical experiences and preceptors believed the nurses were prepared for practice. Sixteen of 19 participants successfully completed the program, which helped resolve the staffing shortage. Novice nurses may benefit from a shadowing experience before applying for this type of program. Leaders in nonperioperative specialties should consider an in-house education program to help meet staffing needs in their areas.

Automating sedation state assessments using natural language processing.

INTRODUCTION: Common goals for procedural sedation are to control pain and ensure the patient is not moving to an extent that is impeding safe progress or completion of the procedure. Clinicians perform regular assessments of the adequacy of procedural sedation in accordance with these goals to inform their decision-making around sedation titration and also for documentation of the care provided. Natural language processing could be applied to real-time transcriptions of audio recordings made during procedures in order to classify sedation states that involve movement and pain, which could then be integrated into clinical documentation systems. The aim of this study was to determine whether natural language processing algorithms will work with sufficient accuracy to detect sedation states during procedural sedation. DESIGN: A prospective observational study was conducted. METHODS: Audio recordings from consenting participants undergoing elective procedures performed in the interventional radiology suite at a large academic hospital were transcribed using an automated speech recognition model. Sentences of transcribed text were used to train and evaluate several different NLP pipelines for a text classification task. The NLP pipelines we evaluated included a simple Bag-of-Words (BOW) model, an ensemble architecture combining a linear BOW model and a "token-to-vector" (Tok2Vec) component, and a transformer-based architecture using the RoBERTa pre-trained model. RESULTS: A total of 15,936 sentences from transcriptions of 82 procedures was included in the analysis. The RoBERTa model achieved the highest performance among the three models with an area under the ROC curve (AUC-ROC) of 0.97, an F1 score of 0.87, a precision of 0.86, and a recall of 0.89. The Ensemble model showed a similarly high AUC-ROC of 0.96, but lower F1 score of 0.79, precision of 0.83, and recall of 0.77. The BOW approach achieved an AUC-ROC of 0.97 and the F1 score was 0.7, precision was 0.83 and recall was 0.66. CONCLUSION: The transformer-based architecture using the RoBERTa pre-trained model achieved the best classification performance. Further research is required to confirm the that this natural language processing pipeline can accurately perform text classifications with real-time audio data to allow for automated sedation state assessments. CLINICAL RELEVANCE: Automating sedation state assessments using natural language processing pipelines would allow for more timely documentation of the care received by sedated patients, and, at the same time, decrease documentation burden for clinicians. Downstream applications can also be generated from the classifications, including for example real-time visualizations of sedation state, which may facilitate improved communication of the adequacy of the sedation between clinicians, who may be performing supervision remotely. Also, accumulation of sedation state assessments from multiple procedures may reveal insights into the efficacy of particular sedative medications or identify procedures where the current approach for sedation and analgesia is not optimal (i.e. a significant amount of time spent in "pain" or "movement" sedation states).

Systematic analysis of alternative exon-dependent interactome remodeling reveals multitasking functions of gene regulatory factors.

Alternative splicing significantly expands biological complexity, particularly in the vertebrate nervous system. Increasing evidence indicates that developmental and tissue-dependent alternative exons often control protein-protein interactions; yet, only a minor fraction of these events have been characterized. Using affinity purification-mass spectrometry (AP-MS), we show that approximately 60% of analyzed neural-differential exons in proteins previously implicated in transcriptional regulation result in the gain or loss of interaction partners, which in some cases form unexpected links with coupled processes. Notably, a neural exon in Chtop regulates its interaction with the Prmt1 methyltransferase and DExD-Box helicases Ddx39b/a, affecting its methylation and activity in promoting RNA export. Additionally, a neural exon in Sap30bp affects interactions with RNA processing factors, modulating a critical function of Sap30bp in promoting the splicing of <100 nt "mini-introns" that control nuclear RNA levels. AP-MS is thus a powerful approach for elucidating the multifaceted functions of proteins imparted by context-dependent alternative exons.

Mechanisms underlying linear ubiquitination and implications in tumorigenesis and drug discovery.

Linear ubiquitination is a distinct type of ubiquitination that involves attaching a head-to-tail polyubiquitin chain to a substrate protein. Early studies found that linear ubiquitin chains are essential for the TNFα- and IL-1-mediated NF-κB signaling pathways. However, recent studies have discovered at least sixteen linear ubiquitination substrates, which exhibit a broader activity than expected and mediate many other signaling pathways beyond NF-κB signaling. Dysregulation of linear ubiquitination in these pathways has been linked to many types of cancers, such as lymphoma, liver cancer, and breast cancer. Since the discovery of linear ubiquitin, extensive effort has been made to delineate the molecular mechanisms of how dysregulation of linear ubiquitination causes tumorigenesis and cancer development. In this review, we highlight newly discovered linear ubiquitination-mediated signaling pathways, recent advances in the role of linear ubiquitin in different types of cancers, and the development of linear ubiquitin inhibitors. Video Abstract.

Metabolome-wide Mendelian randomization characterizes heterogeneous and shared causal effects of metabolites on human health.

Metabolites are small molecules that are useful for estimating disease risk and elucidating disease biology. Nevertheless, their causal effects on human diseases have not been evaluated comprehensively. We performed two-sample Mendelian randomization to systematically infer the causal effects of 1,099 plasma metabolites measured in 6,136 Finnish men from the METSIM study on risk of 2,099 binary disease endpoints measured in 309,154 Finnish individuals from FinnGen. We identified evidence for 282 causal effects of 70 metabolites on 183 disease endpoints (FDR<1%). We found 25 metabolites with potential causal effects across multiple disease domains, including ascorbic acid 2-sulfate affecting 26 disease endpoints in 12 disease domains. Our study suggests that N-acetyl-2-aminooctanoate and glycocholenate sulfate affect risk of atrial fibrillation through two distinct metabolic pathways and that N-methylpipecolate may mediate the causal effect of N6, N6-dimethyllysine on anxious personality disorder. This study highlights the broad causal impact of plasma metabolites and widespread metabolic connections across diseases.

Pamrevlumab, a Fully Human Monoclonal Antibody Targeting Connective Tissue Growth Factor, for Non-Ambulatory Patients with Duchenne Muscular Dystrophy.

BACKGROUND: Duchenne muscular dystrophy (DMD) is a neuromuscular disease stemming from dystrophin gene mutations. Lack of dystrophin leads to progressive muscle damage and replacement of muscle with fibrotic and adipose tissue. Pamrevlumab (FG-3019), a fully human monoclonal antibody that binds to connective tissue growth factor (CTGF), is in Phase III development for treatment of DMD and other diseases. METHODS: MISSION (Study 079; NCT02606136) was an open-label, Phase II, single-arm trial of pamrevlumab in 21 non-ambulatory patients with DMD (aged≥12 years, receiving corticosteroids) who received 35-mg/kg intravenous infusions every 2 weeks for 2 years. The primary endpoint was change from baseline in percent predicted forced vital capacity (ppFVC). Secondary endpoints included other pulmonary function tests, upper limb function and strength assessments, and changes in upper arm fat and fibrosis scores on magnetic resonance imaging. RESULTS: Fifteen patients completed the trial. Annual change from baseline (SE) in ppFVC was -4.2 (0.7) (95% CI -5.5, -2.8). Rate of decline in ppFVC in pamrevlumab-treated patients was slower than observed in historical published trials of non-ambulatory patients. MISSION participants experienced slower-than-anticipated muscle function declines compared with natural history and historical published trials of non-ambulatory patients with DMD. Pamrevlumab was well-tolerated. Treatment-emergent adverse events were mild to moderate, and none led to study discontinuation. CONCLUSIONS: nti-CTGF therapy with pamrevlumab represents a potential treatment for DMD. The lack of internal control group limits the results.

Excitation Intensity-Dependent Quantum Yield of Semiconductor Nanocrystals.

One of the key phenomena that determine the fluorescence of nanocrystals is the nonradiative Auger-Meitner recombination of excitons. This nonradiative rate affects the nanocrystals' fluorescence intensity, excited state lifetime, and quantum yield. Whereas most of the above properties can be directly measured, the quantum yield is the most difficult to assess. Here we place semiconductor nanocrystals inside a tunable plasmonic nanocavity with subwavelength spacing and modulate their radiative de-excitation rate by changing the cavity size. This allows us to determine absolute values of their fluorescence quantum yield under specific excitation conditions. Moreover, as expected considering the enhanced Auger-Meitner rate for higher multiple excited states, increasing the excitation rate reduces the quantum yield of the nanocrystals.

SARS-CoV-2 infection of airway organoids reveals conserved use of Tetraspanin-8 by Ancestral, Delta, and Omicron variants.

Ancestral SARS coronavirus-2 (SARS-CoV-2) and variants of concern (VOC) caused a global pandemic with a spectrum of disease severity. The mechanistic explaining variations related to airway epithelium are relatively understudied. Here, we biobanked airway organoids (AO) by preserving stem cell function. We optimized viral infection with H1N1/PR8 and comprehensively characterized epithelial responses to SARS-CoV-2 infection in phenotypically stable AO from 20 different subjects. We discovered Tetraspanin-8 (TSPAN8) as a facilitator of SARS-CoV-2 infection. TSPAN8 facilitates SARS-CoV-2 infection rates independently of ACE2-Spike interaction. In head-to-head comparisons with Ancestral SARS-CoV-2, Delta and Omicron VOC displayed lower overall infection rates of AO but triggered changes in epithelial response. All variants shared highest tropism for ciliated and goblet cells. TSPAN8-blocking antibodies diminish SARS-CoV-2 infection and may spur novel avenues for COVID-19 therapy.

Direct RNA sequencing of respiratory syncytial virus infected human cells generates a detailed overview of RSV polycistronic mRNA and transcript abundance.

To characterize species of viral mRNA transcripts generated during respiratory syncytial virus (RSV) infection, human fibroblast-like MRC-5 lung cells were infected with subgroup A RSV for 6, 16 and 24 hours. In addition, we characterised the viral transcriptome in infected Calu-3 lung epithelial cells at 48 hours post infection. Total RNA was harvested and polyadenylated mRNA was enriched and sequenced by direct RNA sequencing using an Oxford nanopore device. This platform yielded over 450,000 direct mRNA transcript reads which were mapped to the viral genome and analysed to determine the relative mRNA levels of viral genes using our in-house ORF-centric pipeline. We examined the frequency of polycistronic readthrough mRNAs were generated and assessed the length of the polyadenylated tails for each group of transcripts. We show a general but non-linear decline in gene transcript abundance across the viral genome, as predicted by the model of RSV gene transcription. However, the decline in transcript abundance is not uniform. The polyadenylate tails generated by the viral polymerase are similar in length to those generated by the host polyadenylation machinery and broadly declined in length for most transcripts as the infection progressed. Finally, we observed that the steady state abundance of transcripts with very short polyadenylate tails less than 20 nucleotides is less for N, SH and G transcripts in both cell lines compared to NS1, NS2, P, M, F and M2 which may reflect differences in mRNA stability and/or translation rates within and between the cell lines.

Systematic exploration of dynamic splicing networks reveals conserved multistage regulators of neurogenesis.

Alternative splicing (AS) is a critical regulatory layer; yet, factors controlling functionally coordinated splicing programs during developmental transitions are poorly understood. Here, we employ a screening strategy to identify factors controlling dynamic splicing events important for mammalian neurogenesis. Among previously unknown regulators, Rbm38 acts widely to negatively control neural AS, in part through interactions mediated by the established repressor of splicing, Ptbp1. Puf60, a ubiquitous factor, is surprisingly found to promote neural splicing patterns. This activity requires a conserved, neural-differential exon that remodels Puf60 co-factor interactions. Ablation of this exon rewires distinct AS networks in embryonic stem cells and at different stages of mouse neurogenesis. Single-cell transcriptome analyses further reveal distinct roles for Rbm38 and Puf60 isoforms in establishing neuronal identity. Our results describe important roles for previously unknown regulators of neurogenesis and establish how an alternative exon in a widely expressed splicing factor orchestrates temporal control over cell differentiation.

Nuclear soluble cGAS senses double-stranded DNA virus infection.

The DNA sensor cGAS detects cytosolic DNA and instigates type I interferon (IFN) expression. Recent studies find that cGAS also localizes in the nucleus and binds the chromatin. Despite the mechanism controlling nuclear cGAS activation is well elucidated, whether nuclear cGAS participates in DNA sensing is unclear. Here, we report that herpes simplex virus 1 (HSV-1) infection caused the release of cGAS from the chromatin into the nuclear soluble fraction. Like its cytosolic counterpart, the leaked nuclear soluble cGAS also sensed viral DNA, produced cGAMP, and induced mRNA expression of type I IFN and interferon-stimulated genes. Consistently, the nuclear soluble cGAS limited HSV-1 infection. Furthermore, enzyme-deficient mutation (D307A) or cGAS inhibitor RU.251 abolished nuclear cGAS-mediated innate immune responses, suggesting that enzymatic activity is also required for nuclear soluble cGAS. Taken all together, our study demonstrates that nuclear soluble cGAS acts as a nuclear DNA sensor detecting nuclear-replicating DNA viruses.

Genetic and immunologic features of recurrent stage I lung adenocarcinoma.

Although surgery for early-stage lung cancer offers the best chance of cure, recurrence still occurs between 30 and 50% of the time. Why patients frequently recur after complete resection of early-stage lung cancer remains unclear. Using a large cohort of stage I lung adenocarcinoma patients, distinct genetic, genomic, epigenetic, and immunologic profiles of recurrent tumors were analyzed using a novel recurrence classifier. To characterize the tumor immune microenvironment of recurrent stage I tumors, unique tumor-infiltrating immune population markers were identified using single cell RNA-seq on a separate cohort of patients undergoing stage I lung adenocarcinoma resection and applied to a large study cohort using digital cytometry. Recurrent stage I lung adenocarcinomas demonstrated higher mutation and lower methylation burden than non-recurrent tumors, as well as widespread activation of known cancer and cell cycle pathways. Simultaneously, recurrent tumors displayed downregulation of immune response pathways including antigen presentation and Th1/Th2 activation. Recurrent tumors were depleted in adaptive immune populations, and depletion of adaptive immune populations and low cytolytic activity were prognostic of stage I recurrence. Genomic instability and impaired adaptive immune responses are key features of stage I lung adenocarcinoma immunosurveillance escape and recurrence after surgery.

Opioid prescribing among new users for non-cancer pain in the USA, Canada, UK, and Taiwan: A population-based cohort study.

BACKGROUND: The opioid epidemic in North America has been driven by an increase in the use and potency of prescription opioids, with ensuing excessive opioid-related deaths. Internationally, there are lower rates of opioid-related mortality, possibly because of differences in prescribing and health system policies. Our aim was to compare opioid prescribing rates in patients without cancer, across 5 centers in 4 countries. In addition, we evaluated differences in the type, strength, and starting dose of medication and whether these characteristics changed over time. METHODS AND FINDINGS: We conducted a retrospective multicenter cohort study of adults who are new users of opioids without prior cancer. Electronic health records and administrative health records from Boston (United States), Quebec and Alberta (Canada), United Kingdom, and Taiwan were used to identify patients between 2006 and 2015. Standard dosages in morphine milligram equivalents (MMEs) were calculated according to The Centers for Disease Control and Prevention. Age- and sex-standardized opioid prescribing rates were calculated for each jurisdiction. Of the 2,542,890 patients included, 44,690 were from Boston (US), 1,420,136 Alberta, 26,871 Quebec (Canada), 1,012,939 UK, and 38,254 Taiwan. The highest standardized opioid prescribing rates in 2014 were observed in Alberta at 66/1,000 persons compared to 52, 51, and 18/1,000 in the UK, US, and Quebec, respectively. The median MME/day (IQR) at initiation was highest in Boston at 38 (20 to 45); followed by Quebec, 27 (18 to 43); Alberta, 23 (9 to 38); UK, 12 (7 to 20); and Taiwan, 8 (4 to 11). Oxycodone was the first prescribed opioid in 65% of patients in the US cohort compared to 14% in Quebec, 4% in Alberta, 0.1% in the UK, and none in Taiwan. One of the limitations was that data were not available from all centers for the entirety of the 10-year period. CONCLUSIONS: In this study, we observed substantial differences in opioid prescribing practices for non-cancer pain between jurisdictions. The preference to start patients on higher MME/day and more potent opioids in North America may be a contributing cause to the opioid epidemic.

A Deep Learning Model to Predict Knee Osteoarthritis Based on Nonimage Longitudinal Medical Record.

PURPOSE: To develop deep learning model (Deep-KOA) that can predict the risk of knee osteoarthritis (KOA) within the next year by using the previous three years nonimage-based electronic medical record (EMR) data. PATIENTS AND METHODS: We randomly selected information of two million patients from the Taiwan National Health Insurance Research Database (NHIRD) from January 1, 1999 to December 31, 2013. During the study period, 132,594 patients were diagnosed with KOA, while 1,068,464 patients without KOA were chosen randomly as control. We constructed a feature matrix by using the three-year history of sequential diagnoses, drug prescriptions, age, and sex. Deep learning methods of convolutional neural network (CNN) and artificial neural network (ANN) were used together to develop a risk prediction model. We used the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and precision to evaluate the performance of Deep-KOA. Then, we explored the important features using stepwise feature selection. RESULTS: This study included 132,594 KOA patients, 83,111 females (62.68%), 49,483 males (37.32%), mean age 64.2 years, and 1,068,464 non-KOA patients, 545,902 females (51.09%), 522,562 males (48.91%), mean age 51.00 years. The Deep-KOA achieved an overall AUROC, sensitivity, specificity, and precision of 0.97, 0.89, 0.93, and 0.80 respectively. The discriminative analysis of Deep-KOA showed important features from several diseases such as disorders of the eye and adnexa, acute respiratory infection, other metabolic and immunity disorders, and diseases of the musculoskeletal and connective tissue. Age and sex were not found as the most discriminative features, with AUROC of 0.9593 (-0.76% loss) and 0.9644 (-0.25% loss) respectively. Whereas medications including antacid, cough suppressant, and expectorants were identified as discriminative features. CONCLUSION: Deep-KOA was developed to predict the risk of KOA within one year earlier, which may provide clues for clinical decision support systems to target patients with high risk of KOA to get precision prevention program.

Non-alcoholic Steatohepatitis Pathogenesis, Diagnosis, and Treatment.

There has been a rise in the prevalence of non-alcohol fatty liver disease (NAFLD) due to the popularity of western diets and sedentary lifestyles. One quarter of NAFLD patients is diagnosed with non-alcoholic steatohepatitis (NASH), with histological evidence not only of fat accumulation in hepatocytes but also of liver cell injury and death due to long-term inflammation. Severe NASH patients have increased risks of cirrhosis and liver cancer. In this review, we discuss the pathogenesis and current methods of diagnosis for NASH, and current status of drug development for this life-threatening liver disease.

Digital interventions self-management education for type 1 and 2 diabetes: A systematic review and meta-analysis.

OBJECTIVE: To describe and assess digital health-led diabetes self-management education and support (DSMES) effectiveness in improving glycosylated hemoglobin, diabetes knowledge, and health-related quality of life (HrQoL) of Type 1 and 2 Diabetes in the past 10 years. DESIGN: Systematic Review and Meta-Analysis. The protocol was registered on PROSPERO registration number CRD42019139884. DATA SOURCES: PubMed, EMBASE, Cochrane library, Web of Science, and Scopus between January 2010 and August 2019. Study Selection and Appraisal: Randomized control trials of digital health-led DSMES for Type 1 (T1DM) or 2 (T2DM) diabetes compared to usual care were included. Outcomes were change in HbA1c, diabetes knowledge, and HrQoL. Cochrane Risk of Bias 2.0 tool was used to assess bias and GRADEpro for overall quality. The analysis involved narrative synthesis, subgroup and pooled meta-analyses. RESULTS: From 4286 articles, 39 studies (6861 participants) were included. Mean age was 51.62 years, range (13-70). Meta-analysis revealed intervention effects on HbA1c for T2DM with difference in means (MD) from baseline -0.480% (-0.661, -0.299), I275% (6 months), -0.457% (-0.761, -0.151), I2 81% (12 months), and for T1DM -0.41% (-1.022, 0.208) I2 83% (6 months), -0.03% (-0.210, 0.142) I2 0% (12 months). Few reported HrQoL with Hedges' g 0.183 (-0.039, 0.405), I2 0% (6 months), 0.153 (-0.060, 0.366), I2 0% (12 months) and diabetes knowledge with Hedges' g 1.003 (0.068, 1.938), I2 87% (3 months). CONCLUSION: Digital health-led DSMES are effective in improving HbA1c and diabetes knowledge, notably for T2DM. Research shows non-significant changes in HrQoL. Intervention effect on HbA1c was more impressive if delivered through mobile apps or patient portals. Further research is needed on the impact of DSMES on these outcomes, especially for newly diagnosed diabetes patients.

SARS-CoV-2 infection studies in lung organoids identify TSPAN8 as novel mediator.

SARS coronavirus-2 (SARS-CoV-2) is causing a global pandemic with large variation in COVID-19 disease spectrum. SARS-CoV-2 infection requires host receptor ACE2 on lung epithelium, but epithelial underpinnings of variation are largely unknown. We capitalized on comprehensive organoid assays to report remarkable variation in SARS-CoV-2 infection rates of lung organoids from different subjects. Tropism is highest for TUBA- and MUC5AC-positive organoid cells, but levels of TUBA-, MUC5A-, or ACE2- positive cells do not predict infection rate. We identify surface molecule Tetraspanin 8 (TSPAN8) as novel mediator of SARS-CoV-2 infection, which is not downregulated by this specific virus. TSPAN8 levels, prior to infection, strongly correlate with infection rate and TSPAN8-blocking antibodies diminish SARS-CoV-2 infection. We propose TSPAN8 as novel functional biomarker and potential therapeutic target for COVID-19.

Deep Learning Classifier with Patient's Metadata of Dermoscopic Images in Malignant Melanoma Detection.

BACKGROUND: Incidence of skin cancer is one of the global burdens of malignancies that increase each year, with melanoma being the deadliest one. Imaging-based automated skin cancer detection still remains challenging owing to variability in the skin lesions and limited standard dataset availability. Recent research indicates the potential of deep convolutional neural networks (CNN) in predicting outcomes from simple as well as highly complicated images. However, its implementation requires high-class computational facility, that is not feasible in low resource and remote areas of health care. There is potential in combining image and patient's metadata, but the study is still lacking. OBJECTIVE: We want to develop malignant melanoma detection based on dermoscopic images and patient's metadata using an artificial intelligence (AI) model that will work on low-resource devices. METHODS: We used an open-access dermatology repository of International Skin Imaging Collaboration (ISIC) Archive dataset consist of 23,801 biopsy-proven dermoscopic images. We tested performance for binary classification malignant melanomas vs nonmalignant melanomas. From 1200 sample images, we split the data for training (72%), validation (18%), and testing (10%). We compared CNN with image data only (CNN model) vs CNN for image data combined with an artificial neural network (ANN) for patient's metadata (CNN+ANN model). RESULTS: The balanced accuracy for CNN+ANN model was higher (92.34%) than the CNN model (73.69%). Combination of the patient's metadata using ANN prevents the overfitting that occurs in the CNN model using dermoscopic images only. This small size (24 MB) of this model made it possible to run on a medium class computer without the need of cloud computing, suitable for deployment on devices with limited resources. CONCLUSION: The CNN+ANN model can increase the accuracy of classification in malignant melanoma detection even with limited data and is promising for development as a screening device in remote and low resources health care.