Extracellular Vesicles from Pancreatic Cancer Stem Cells Lead an Intratumor Communication Network (EVNet) to fuel tumour progression.

OBJECTIVE: Intratumor heterogeneity drives cancer progression and therapy resistance. However, it has yet to be determined whether and how subpopulations of cancer cells interact and how this interaction affects the tumour. DESIGN: We have studied the spontaneous flow of extracellular vesicles (EVs) between subpopulations of cancer cells: cancer stem cells (CSC) and non-stem cancer cells (NSCC). To determine the biological significance of the most frequent communication route, we used pancreatic ductal adenocarcinoma (PDAC) orthotopic models, patient-derived xenografts (PDXs) and genetically engineered mouse models (GEMMs). RESULTS: We demonstrate that PDAC tumours establish an organised communication network between subpopulations of cancer cells using EVs called the EVNet). The EVNet is plastic and reshapes in response to its environment. Communication within the EVNet occurs preferentially from CSC to NSCC. Inhibition of this communication route by impairing Rab27a function in orthotopic xenographs, GEMMs and PDXs is sufficient to hamper tumour growth and phenocopies the inhibition of communication in the whole tumour. Mechanistically, we provide evidence that CSC EVs use agrin protein to promote Yes1 associated transcriptional regulator (YAP) activation via LDL receptor related protein 4 (LRP-4). Ex vivo treatment of PDXs with antiagrin significantly impairs proliferation and decreases the levels of activated YAP.Patients with high levels of agrin and low inactive YAP show worse disease-free survival. In addition, patients with a higher number of circulating agrin+ EVs show a significant increased risk of disease progression. CONCLUSION: PDAC tumours establish a cooperation network mediated by EVs that is led by CSC and agrin, which allows tumours to adapt and thrive. Targeting agrin could make targeted therapy possible for patients with PDAC and has a significant impact on CSC that feeds the tumour and is at the centre of therapy resistance.

The value of cell-free circulating tumour DNA profiling in advanced non-small cell lung cancer (NSCLC) management.

Liquid biopsy (LB) has boosted a remarkable change in the management of cancer patients by contributing to tumour genomic profiling. Plasma circulating cell-free tumour DNA (ctDNA) is the most widely searched tumour-related element for clinical application. Specifically, for patients with lung cancer, LB has revealed valuable to detect the diversity of targetable genomic alterations and to detect and monitor the emergence of resistance mechanisms. Furthermore, its non-invasive nature helps to overcome the difficulty in obtaining tissue samples, offering a comprehensive view about tumour diversity. However, the use of the LB to support diagnostic and therapeutic decisions still needs further clarification. In this sense, this review aims to provide a critical view of the clinical importance of plasma ctDNA analysis, the most widely applied LB, and its limitations while anticipating concepts that will intersect the present and future of LB in non-small cell lung cancer patients.

The Adaptive Immune Landscape of the Colorectal Adenoma-Carcinoma Sequence.

BACKGROUND: The tumor immune microenvironment exerts a pivotal influence in tumor initiation and progression. The aim of this study was to analyze the immune context of sporadic and familial adenomatous polyposis (FAP) lesions along the colorectal adenoma-carcinoma sequence (ACS). METHODS: We analyzed immune cell counts (CD3+, CD4+, CD8+, Foxp3+, and CD57+), tumor mutation burden (TMB), MHC-I expression and PD-L1 expression of 59 FAP and 74 sporadic colorectal lesions, encompassing adenomas with low-grade dysplasia (LGD) (30 FAP; 30 sporadic), adenomas with high-grade dysplasia (22 FAP; 30 sporadic), and invasive adenocarcinomas (7 FAP; 14 sporadic). RESULTS: The sporadic colorectal ACS was characterized by (1) a stepwise decrease in immune cell counts, (2) an increase in TMB and MHC-I expression, and (3) a lower PD-L1 expression. In FAP lesions, we observed the same patterns, except for an increase in TMB along the ACS. FAP LGD lesions harbored lower Foxp3+ T cell counts than sporadic LGD lesions. A decrease in PD-L1 expression occurred earlier in FAP lesions compared to sporadic ones. CONCLUSIONS: The colorectal ACS is characterized by a progressive loss of adaptive immune infiltrate and by the establishment of a progressively immune cold microenvironment. These changes do not appear to be related with the loss of immunogenicity of tumor cells, or to the onset of an immunosuppressive tumor microenvironment.

Simultaneous detection of lung fusions using a multiplex RT-PCR next generation sequencing-based approach: a multi-institutional research study.

BACKGROUND: Gene fusion events resulting from chromosomal rearrangements play an important role in initiation of lung adenocarcinoma. The recent association of four oncogenic driver genes, ALK, ROS1, RET, and NTRK1, as lung tumor predictive biomarkers has increased the need for development of up-to-date technologies for detection of these biomarkers in limited amounts of material. METHODS: We describe here a multi-institutional study using the Ion AmpliSeq™ RNA Fusion Lung Cancer Research Panel to interrogate previously characterized lung tumor samples. RESULTS: Reproducibility between laboratories using diluted fusion-positive cell lines was 100%. A cohort of lung clinical research samples from different origins (tissue biopsies, tissue resections, lymph nodes and pleural fluid samples) were used to evaluate the panel. We observed 97% concordance for ALK (28/30 positive; 71/70 negative samples), 95% for ROS1 (3/4 positive; 19/18 negative samples), and 93% for RET (2/1 positive; 13/14 negative samples) between the AmpliSeq assay and other methodologies. CONCLUSION: This methodology enables simultaneous detection of multiple ALK, ROS1, RET, and NTRK1 gene fusion transcripts in a single panel, enhanced by an integrated analysis solution. The assay performs well on limited amounts of input RNA (10 ng) and offers an integrated single assay solution for detection of actionable fusions in lung adenocarcinoma, with potential savings in both cost and turn-around-time compared to the combination of all four assays by other methods.

New massive parallel sequencing approach improves the genetic characterization of congenital myopathies.

Congenital myopathies (CMs) are a heterogeneous group of muscle diseases characterized by hypotonia, delayed motor skills and muscle weakness with onset during the first years of life. The diagnostic workup of CM is highly dependent on the interpretation of the muscle histology, where typical pathognomonic findings are suggestive of a CM but are not necessarily gene specific. Over 20 loci have been linked to these myopathies, including three exceptionally large genes (TTN, NEB and RYR1), which are a challenge for molecular diagnosis. We developed a new approach using massive parallel sequencing (MPS) technology to simultaneously analyze 20 genes linked to CMs. Assay design was based on the Ion AmpliSeq strategy and sequencing runs were performed on an Ion PGM system. A total of 12 patients were analyzed in this study. Among the 2534 variants detected, 14 pathogenic mutations were successfully identified in the DNM2, NEB, RYR1, SEPN1 and TTN genes. Most of these had not been documented and/or fully characterized, hereby contributing to expand the CM mutational spectrum. The utility of this approach was demonstrated by the identification of mutations in 70% of the patients included in this study, which is relevant for CMs especially considering its wide phenotypic and genetic heterogeneity.

Assessment of the spatial variability in tall wheatgrass forage using LANDSAT 8 satellite imagery to delineate potential management zones.

Little information is available on the degree of within-field variability of potential production of Tall wheatgrass (Thinopyrum ponticum) forage under unirrigated conditions. The aim of this study was to characterize the spatial variability of the accumulated biomass (AB) without nutritional limitations through vegetation indexes, and then use this information to determine potential management zones. A 27-×-27-m grid cell size was chosen and 84 biomass sampling areas (BSA), each 2 m(2) in size, were georeferenced. Nitrogen and phosphorus fertilizers were applied after an initial cut at 3 cm height. At 500 °C day, the AB from each sampling area, was collected and evaluated. The spatial variability of AB was estimated more accurately using the Normalized Difference Vegetation Index (NDVI), calculated from LANDSAT 8 images obtained on 24 November 2014 (NDVInov) and 10 December 2014 (NDVIdec) because the potential AB was highly associated with NDVInov and NDVIdec (r (2)  = 0.85 and 0.83, respectively). These models between the potential AB data and NDVI were evaluated by root mean squared error (RMSE) and relative root mean squared error (RRMSE). This last coefficient was 12 and 15 % for NDVInov and NDVIdec, respectively. Potential AB and NDVI spatial correlation were quantified with semivariograms. The spatial dependence of AB was low. Six classes of NDVI were analyzed for comparison, and two management zones (MZ) were established with them. In order to evaluate if the NDVI method allows us to delimit MZ with different attainable yields, the AB estimated for these MZ were compared through an ANOVA test. The potential AB had significant differences among MZ. Based on these findings, it can be concluded that NDVI obtained from LANDSAT 8 images can be reliably used for creating MZ in soils under permanent pastures dominated by Tall wheatgrass.

Nonoptical massive parallel DNA sequencing of BRCA1 and BRCA2 genes in a diagnostic setting.

The introduction of the benchtop massive parallel sequencers made it possible for the majority of clinical diagnostic laboratories to gain access to this fast evolving technology. In this study, using the Ion Torrent Personal Genome Machine, we present a strategy for the molecular diagnosis of hereditary breast and ovarian cancer and respective analytical validation. The methodology relies on a multiplex PCR amplification of the BRCA1 and BRCA2 genes combined with a variant prioritization pipeline, designed to minimize the number of false-positive calls without the introduction of false-negative results. A training set of samples was used to optimize the entire process, and a second set was used to validate and independently evaluate the performance of the workflow. Performing the study in a blind manner relative to the variants in the samples and using conventional Sanger sequencing as standard, the workflow resulted in a strategy with a maximum analytical sensitivity ≥98.6% with a confidence of 95% and a specificity of 96.9%. Importantly, no true variant was missed. This study presents a comprehensive massive parallel sequencing-Sanger sequencing based strategy, which results in a high analytical sensitivity assay that provides a time- and cost-effective strategy for the identification of mutations in the BRCA1 and BRCA2 genes.

Cancer patient management: Current use of next-generation sequencing in the EU TOP4.

BACKGROUND: Next-generation sequencing (NGS) is recognised by a growing audience of medical professionals as a functional diagnostic tool in oncology. However, adoption in clinical routine proceeds haphazardly in Europe. METHODS: A semi-structured interview survey was administered to 68 cancer care professionals in four EU countries between June-August and November-December 2021. Pre-screening questionnaires assessed sufficient NGS expertise, diverse geographical distribution, and professional roles. RESULTS: Our findings provide a better understanding of current clinical, regulatory, and reimbursement practices for NGS in four EU countries. CONCLUSIONS: Despite the impending European In-vitro Diagnostic Medical Devices Regulation (IVDR), tortuous national guidelines implementations and limping reimbursement policies are common traits across surveyed countries and produce disparity in access to advanced healthcare services amid regional distinctions. POLICY SUMMARY: The evident information gap between involved parties and demand for consistent national guidelines could be filled by health economics analyses tailored to local specifics to provide factual leverage for a structured adoption of NGS testing.

Long-term vinasse application enhanced the initial dissipation of atrazine and ametryn in a sugarcane field in Tucumán, Argentina.

The production of sugarcane bioethanol generates large volumes of vinasse, an effluent whose final disposal can produce an environmental impact that is of concern. The long-term disposal of vinasse in sugarcane fields could challenge crop management, such as the performance of traditional herbicides, by changing soil properties. This study aimed to evaluate the effect of long-term vinasse application on the field and the dissipation of atrazine and ametryn herbicides in a subtropical sugarcane agroecosystem, and to discuss the potential processes involved in it. Vinasse affected soil properties by increasing pH (12%), electrical conductivity (160%), and soil organic carbon (25%) at 0-10 cm depth of soil. Differences in the herbicide calculated sorption coefficient (Kd) varied according to the pedotransfer function applied and the herbicide type (atrazine or ametryn). During the first seven days after herbicide application, the soil underwent long-term vinasse application and increased atrazine and ametryn dissipation 45% and 33%, respectively, compared with the conventional fertilization scheme (control). The Pesticide Root Zone Model revealed that dissipation was mediated mainly by the degradation process rather than transport or other processes. The long-term application of vinasse in a typical sugarcane field of Tucumán, Argentina decreased the potential groundwater pollution of triazines and, adversely, reduced their bioavailability for weed control. For this, the present study presents original information about how long-term treatment with vinasse may require an adaptation of conventional management practices such as the application of herbicides in Argentina and other sugarcane-producing regions. Integr Environ Assess Manag 2023;00:1-12. © 2023 SETAC.

Vitamin D and the mammary gland: a review on its role in normal development and breast cancer.

Breast cancer is a heterogeneous disease associated with diverse biological behaviours and clinical outcome. Although some molecular subgroups of breast cancer have a targeted therapy, the most aggressive tumours still lack a molecular target. Despite vitamin D being classically associated with the physiological role of calcium regulation and phosphate transport in bone metabolism, several studies have demonstrated a wide range of functions for this hormone, which are particularly important in the field of cancer. The mechanisms underlying the protective actions of vitamin D in cancer development are only sparsely understood, but evidence shows that vitamin D participates in cell growth regulation, apoptosis and cell differentiation. In addition, it has been implicated in the suppression of cancer cell invasion, angiogenesis and metastasis. Most of vitamin D biological actions are mediated by the vitamin D receptor and the synthesis and catabolism of this hormone are regulated by the enzymes CYP27B1 and CYP24A1. In the present review we highlight research data concerning the function of this hormone in the mammary gland, with a special focus on breast carcinogenesis. Hence, and although the available data are controversial, we consider not only updated information on the epidemiology of vitamin D in breast cancer and its potential value as a therapeutic agent or prophylactic (with an emphasis on molecular mechanisms and effectors of vitamin D action), but include data on its role in other stages of breast cancer progression as well. Accordingly, we review data on the influence of vitamin D in the development of normal breast and the expression of vitamin D-related proteins (VDR, CYP27B1 and CYP24A21) in benign mammary lesions and ductal carcinomas in situ.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges.

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

Multiple instance learning for lung pathophysiological findings detection using CT scans.

Lung diseases affect the lives of billions of people worldwide, and 4 million people, each year, die prematurely due to this condition. These pathologies are characterized by specific imagiological findings in CT scans. The traditional Computer-Aided Diagnosis (CAD) approaches have been showing promising results to help clinicians; however, CADs normally consider a small part of the medical image for analysis, excluding possible relevant information for clinical evaluation. Multiple Instance Learning (MIL) approach takes into consideration different small pieces that are relevant for the final classification and creates a comprehensive analysis of pathophysiological changes. This study uses MIL-based approaches to identify the presence of lung pathophysiological findings in CT scans for the characterization of lung disease development. This work was focus on the detection of the following: Fibrosis, Emphysema, Satellite Nodules in Primary Lesion Lobe, Nodules in Contralateral Lung and Ground Glass, being Fibrosis and Emphysema the ones with more outstanding results, reaching an Area Under the Curve (AUC) of 0.89 and 0.72, respectively. Additionally, the MIL-based approach was used for EGFR mutation status prediction - the most relevant oncogene on lung cancer, with an AUC of 0.69. The results showed that this comprehensive approach can be a useful tool for lung pathophysiological characterization.

An Interpretable Approach for Lung Cancer Prediction and Subtype Classification using Gene Expression.

Lung cancer is the deadliest form of cancer, accounting for 20% of total cancer deaths. It represents a group of histologically and molecularly heterogeneous diseases even within the same histological subtype. Moreover, accurate histological subtype diagnosis influences the specific subtype's target genes, which will help define the treatment plan to target those genes in therapy. Deep learning (DL) models seem to set the benchmarks for the tasks of cancer prediction and subtype classification when using gene expression data; however, these methods do not provide interpretability, which is great concern from the perspective of cancer biology since the identification of the cancer driver genes in an individual provides essential information for treatment and prognosis. In this work, we identify some limitations of previous work that showed efforts to build algorithms to extract feature weights from DL models, and we propose using tree-based learning algorithms that address these limitations. Preliminary results show that our methods outperform those of related research while providing model interpretability.Clinical Relevance: The machine learning methods used in this work are interpretable and provide biological insight. Two sets of genes were extracted: a set that differentiates normal tissue from cancerous tissue (cancer prediction), and a set of genes that distinguishes LUAD from LUSC samples (subtype classification).

Attention Based Deep Multiple Instance Learning Approach for Lung Cancer Prediction using Histopathological Images.

Deep Neural Networks using histopathological images as an input currently embody one of the gold standards in automated lung cancer diagnostic solutions, with Deep Convolutional Neural Networks achieving the state of the art values for tissue type classification. One of the main reasons for such results is the increasing availability of voluminous amounts of data, acquired through the efforts employed by extensive projects like The Cancer Genome Atlas. Nonetheless, whole slide images remain weakly annotated, as most common pathologist annotations refer to the entirety of the image and not to individual regions of interest in the patient's tissue sample. Recent works have demonstrated Multiple Instance Learning as a successful approach in classification tasks entangled with this lack of annotation, by representing images as a bag of instances where a single label is available for the whole bag. Thus, we propose a bag/embedding-level lung tissue type classifier using Multiple Instance Learning, where the automated inspection of lung biopsy whole slide images determines the presence of cancer in a given patient. Furthermore, we use a post-model interpretability algorithm to validate our model's predictions and highlight the regions of interest for such predictions.

Monensin occurrence in surface water and its impact on aquatic biota in a stream of the southeast Pampas, Argentina.

Monensin is an ionophore antibiotic used as a feed additive and growth promoter in cattle production worldwide. The occurrence of monensin in aquatic surficial ecosystems is of concern due to its possible detrimental effects on human health and native biota. Argentina is one of the most important cattle beef producers worldwide; however, there is little knowledge on the environmental occurrence of monensin and the associated risks to aquatic biota. In this study, we developed a method for the extraction and quantification of monensin in surface water; then, we evaluated the occurrence of monensin in a stream impacted by different animal husbandry's operations, and then, we analyzed the ecological implications of monensin residues on aquatic organisms using the risk quotient (RQ) method. Sampling was carried out on August 2017 from the headwaters to the floodplain of the El Pantanoso stream, Buenos Aires province, Argentina. Monensin detection frequency was 75% (n = 20). The median level was 0.40 µg/L and the maximum concentration was 4.70 µg/L. The main input of monensin was from a cattle slaughterhouse, an activity that has not been considered before in the literature as a source of emission of veterinary pharmaceuticals into the environment. The RQ assessment showed that monensin levels could have potential negative effects on aquatic biota in the sampling site closest to the cattle slaughterhouse. The data obtained in this study shows that monensin was present in El Pantanoso surface waters at levels of high ecotoxicological risk to aquatic biota.

Next generation sequencing for liquid biopsy based testing in non-small cell lung cancer in 2021.

Lung cancer is the leading cause of cancer death worldwide, with non-small cell lung cancer (NSCLC) representing its most commonly diagnosed sub-type. Despite the significant improvements in lung cancer biomarkers knowledge, accompanied by substantial technological advances in molecular tumor profiling, a considerable fraction (up to 30 %) of advanced NSCLC patient presents with major testing challenges or tissue unavailability for molecular analysis. In this context, liquid biopsy is on the rise, currently gaining considerable interest within the molecular pathology and oncology community. Molecular profiling of liquid biopsy specimens using next generation molecular biology methodologies is a rapidly evolving field with promising applications not exclusively limited to advanced stages but also more recently expanding to early stages cancer patients. Here, we offer an overview of some of the most consolidated and emerging applications of next generation sequencing technologies for liquid biopsy testing in NSCLC.

Clinical Application of Next-Generation Sequencing of Plasma Cell-Free DNA for Genotyping Untreated Advanced Non-Small Cell Lung Cancer.

BACKGROUND: Analysis of circulating tumor DNA (ctDNA) has remarkable potential as a non-invasive lung cancer molecular diagnostic method. This prospective study addressed the clinical value of a targeted-gene amplicon-based plasma next-generation sequencing (NGS) assay to detect actionable mutations in ctDNA in patients with newly diagnosed advanced lung adenocarcinoma. METHODS: ctDNA test performance and concordance with tissue NGS were determined, and the correlation between ctDNA findings, clinical features, and clinical outcomes was evaluated in 115 patients with paired plasma and tissue samples. RESULTS: Targeted-gene NGS-based ctDNA and NGS-based tissue analysis detected 54 and 63 genomic alterations, respectively; 11 patients presented co-mutations, totalizing 66 hotspot mutations detected, 51 on both tissue and plasma, 12 exclusively on tissue, and 3 exclusively on plasma. NGS-based ctDNA revealed a diagnostic performance with 81.0% sensitivity, 95.3% specificity, 94.4% PPV, 83.6% NPV, test accuracy of 88.2%, and Cohen's Kappa 0.764. PFS and OS assessed by both assays did not significantly differ. Detection of ctDNA alterations was statistically associated with metastatic disease (p = 0.013), extra-thoracic metastasis (p = 0.004) and the number of organs involved (p = 0.010). CONCLUSIONS: This study highlights the potential use of ctDNA for mutation detection in newly diagnosed NSCLC patients due to its high accuracy and correlation with clinical outcomes.

The Role of Liquid Biopsy in Early Diagnosis of Lung Cancer.

Liquid biopsy is an emerging technology with a potential role in the screening and early detection of lung cancer. Several liquid biopsy-derived biomarkers have been identified and are currently under ongoing investigation. In this article, we review the available data on the use of circulating biomarkers for the early detection of lung cancer, focusing on the circulating tumor cells, circulating cell-free DNA, circulating micro-RNAs, tumor-derived exosomes, and tumor-educated platelets, providing an overview of future potential applicability in the clinical practice. While several biomarkers have shown exciting results, diagnostic performance and clinical applicability is still limited. The combination of different biomarkers, as well as their combination with other diagnostic tools show great promise, although further research is still required to define and validate the role of liquid biopsies in clinical practice.

Targeting p53 for Melanoma Treatment: Counteracting Tumour Proliferation, Dissemination and Therapeutic Resistance.

Melanoma is the deadliest form of skin cancer, primarily due to its high metastatic propensity and therapeutic resistance in advanced stages. The frequent inactivation of the p53 tumour suppressor protein in melanomagenesis may predict promising outcomes for p53 activators in melanoma therapy. Herein, we aimed to investigate the antitumor potential of the p53-activating agent SLMP53-2 against melanoma. Two- and three-dimensional cell cultures and xenograft mouse models were used to unveil the antitumor activity and the underlying molecular mechanism of SLMP53-2 in melanoma. SLMP53-2 inhibited the growth of human melanoma cells in a p53-dependent manner through induction of cell cycle arrest and apoptosis. Notably, SLMP53-2 induced p53 stabilization by disrupting the p53-MDM2 interaction, enhancing p53 transcriptional activity. It also promoted the expression of p53-regulated microRNAs (miRNAs), including miR-145 and miR-23a. Moreover, it displayed anti-invasive and antimigratory properties in melanoma cells by inhibiting the epithelial-to-mesenchymal transition (EMT), angiogenesis and extracellular lactate production. Importantly, SLMP53-2 did not induce resistance in melanoma cells. Additionally, it synergized with vemurafenib, dacarbazine and cisplatin, and resensitized vemurafenib-resistant cells. SLMP53-2 also exhibited antitumor activity in human melanoma xenograft mouse models by repressing cell proliferation and EMT while stimulating apoptosis. This work discloses the p53-activating agent SLMP53-2 which has promising therapeutic potential in advanced melanoma, either as a single agent or in combination therapy. By targeting p53, SLMP53-2 may counteract major features of melanoma aggressiveness.

Sharing Biomedical Data: Strengthening AI Development in Healthcare.

Artificial intelligence (AI)-based solutions have revolutionized our world, using extensive datasets and computational resources to create automatic tools for complex tasks that, until now, have been performed by humans. Massive data is a fundamental aspect of the most powerful AI-based algorithms. However, for AI-based healthcare solutions, there are several socioeconomic, technical/infrastructural, and most importantly, legal restrictions, which limit the large collection and access of biomedical data, especially medical imaging. To overcome this important limitation, several alternative solutions have been suggested, including transfer learning approaches, generation of artificial data, adoption of blockchain technology, and creation of an infrastructure composed of anonymous and abstract data. However, none of these strategies is currently able to completely solve this challenge. The need to build large datasets that can be used to develop healthcare solutions deserves special attention from the scientific community, clinicians, all the healthcare players, engineers, ethicists, legislators, and society in general. This paper offers an overview of the data limitation in medical predictive models; its impact on the development of healthcare solutions; benefits and barriers of sharing data; and finally, suggests future directions to overcome data limitations in the medical field and enable AI to enhance healthcare. This perspective is dedicated to the technical requirements of the learning models, and it explains the limitation that comes from poor and small datasets in the medical domain and the technical options that try or can solve the problem related to the lack of massive healthcare data.