Medical Disease Diagnosis Research Articles

Medical Diagnosis using Machine Learning

Machine learning is one of the fast growing aspect in current world. Machine learning (ML) and Artificial neural network (ANN) are helpful in medical diagnostic task, detection and diagnosis of various disease. The information required for diagnosis is typically gathered from a history and physical examination of the person who is in need of medical care. The aim of this paper to examine the applications of machine learning and artificial neural network in medical and data science field. In specific, we have chosen the disease dengue. This targets on dengue fever prediction, symptoms of a patient, using a data mining tool for the accurateness. Climate change is the main cause of dengue. There is a need for active input from health sector to ensure development and prevention about local and global environment.

Optical phase conjugation (OPC) for focusing light through/inside biological tissue

Optical phase conjugation(OPC) is a technique that generates a light field with reversed wavefront and identical amplitude distribution as the incident light. It has a unique feature of suppressing the aberration of incident beam induced by inhomogeneous or disturbing medium. Although this technique has been extensively studied since the 1970s, it has become more attractive because of unprecedented achievements and prospective potentials in biomedical applications. OPC-based techniques have been successfully utilized to form a focus through/inside highly scattered biological samples. It opens a new avenue by significantly enhancing the light delivery in biological tissue for high-resolution imaging, diagnosis and treatment of medical diseases. In order to provide insight into its further development, recent progress of OPC techniques for focusing light through/inside biological tissue was summarized.

Automatic skin lesions segmentation based on a new morphological approach via geodesic active contour

Automatic disease classification has been one of the most intensively searched in recent years due to the possibility of quickly providing a diagnosis to the patient. In this process, the segmentation of regions of interest of these diseases has a fundamental role in their subsequent classification. With skin lesions segmentation it is no different and in recent years many studies have achieved interesting results, becoming an important tool in aiding the medical diagnosis of skin diseases. In this work, a morphological geodesic active contour segmentation (MGAC) method is proposed with automatic initialization, using mathematical morphology which is a great partial differential equation approximation, with lower computational cost, no stability problems and fully automatic. The proposed method was tested in a stable and well-known dermoscopic images database provided by Pedro Hispano Hospital (PH2) and was compared with both methods that make use of machine learning or deep learning techniques such as fully convolutional networks (FCN), full resolution convolutional networks (FrCN), deep class-specific learning with probability based step-wise integration (DCL-PSI), and others, and also traditional methods like JSEG, statistical region merging (SRM), Level Set, ASLM and others. The MGAC showed good results in all similarity metrics compared in this work like Jaccard Index (86.16%), Dice coefficient (92.09%) and Matthew correlation coefficient (87.52%), and also achieves good results in sensitivity (91.72%), specificity (97.99%), accuracy (94.59%) and F-measure (93.82%). Thus, the proposed method presented better results in relation to all these metrics when compared to the traditional methods and still presented better results in relation to the methods that use machine learning or deep learning techniques in Jaccard Index, Dice coefficient and specificity. This confirm that the MGAC can efficiently segment skin lesions, presenting great potential to be applied in the aid of the medical diagnosis.

Comparing laparoscopic and percutaneous renal biopsy for diagnosing native kidney disease: A matched pair analysis

Percutaneous renal biopsy is a well-established diagnostic procedure in patients with underlying medical renal disease. Aim of this study is to compare the adequacy of the biopsy material, the diagnostic yield, and the complication rates of the trans-peritoneal laparoscopic approach and the image-guided percutaneous approach to renal biopsy in the diagnosis of native kidney disease. We performed a matched-pair analysis matching 1:3 40 patients who underwent trans-peritoneal laparoscopic renal biopsy to 120 patients who underwent percutaneous renal biopsy in the same years. Patients were retrospectively analyzed. Differences in adequacy of biopsy material (i.e. number of glomeruli, continuous), diagnostic yield (categorical) and postoperative complications across the two groups were assessed using Wilcoxon Rank sum or χ2 test. Laparoscopic biopsy was associated with a higher number of harbored glomeruli (median 50, IQR 20-77) compared to the percutaneous approach (median 10, IQR 7-15), P<0.001. Adequate biopsies containing at least ten glomeruli were obtained in a significantly higher percentage of patients in the laparoscopic group versus the percutaneous group (92.5% vs. 57.1%, P<0.001). The laparoscopic approach was also associated with a significantly higher diagnostic yield than the percutaneous approach (82.5% vs. 63.5%, P=0.027). Patients who underwent laparoscopic biopsy had no perioperative or postoperative complications, resulting in a significantly lower complication rate than percutaneous biopsy (0% vs. 4%, P<0.001), particularly in the need for transfusion for post-procedure bleeding (0% vs. 1.8%, P<0.001). In this retrospective matched-pair analysis comparing patients undergoing renal biopsy for medical kidney disease, trans-peritoneal laparoscopic renal biopsy was safer and more effective for the diagnosis of medical renal diseases compared to percutaneous renal biopsy. Prospective trials with a good follow-up are needed to define the best candidate for each approach. 4.

Survey of Image Processing Techniques for Brain Pathology Diagnosis: Challenges and Opportunities.

In recent years, a number of new products introduced to the global market combine intelligent robotics, artificial intelligence and smart interfaces to provide powerful tools to support professional decision making. However, while brain disease diagnosis from the brain scan images is supported by imaging robotics, the data analysis to form a medical diagnosis is performed solely by highly trained medical professionals. Recent advances in medical imaging techniques, artificial intelligence, machine learning and computer vision present new opportunities to build intelligent decision support tools to aid the diagnostic process, increase the disease detection accuracy, reduce error, automate the monitoring of patient's recovery, and discover new knowledge about the disease cause and its treatment. This article introduces the topic of medical diagnosis of brain diseases from the MRI based images. We describe existing, multi-modal imaging techniques of the brain's soft tissue and describe in detail how are the resulting images are analyzed by a radiologist to form a diagnosis. Several comparisons between the best results of classifying natural scenes and medical image analysis illustrate the challenges of applying existing image processing techniques to the medical image analysis domain. The survey of medical image processing methods also identified several knowledge gaps, the need for automation of image processing analysis, and the identification of the brain structures in the medical images that differentiate healthy tissue from a pathology. This survey is grounded in the cases of brain tumor analysis and the traumatic brain injury diagnoses, as these two case studies illustrate the vastly different approaches needed to define, extract, and synthesize meaningful information from multiple MRI image sets for a diagnosis. Finally, the article summarizes artificial intelligence frameworks that are built as multi-stage, hybrid, hierarchical information processing work-flows and the benefits of applying these models for medical diagnosis to build intelligent physician's aids with knowledge transparency, expert knowledge embedding, and increased analytical quality.

Diagnostic histochemistry in medical diseases of the kidney.

The value of histochemical analysis in the diagnosis of medical renal diseases has long been known, and its use continues currently. Depending on the particular disorder in question, a variety of "special" stains may be applied to renal biopsies. These include the periodic acid-Schiff, Masson trichrome, Jones, von Kossa, Verhoeff-van Gieson, Congo Red, and toluidine blue methods, among others. This review considers the application of such techniques in the assessment of vascular, glomerular, and tubulointerstitial lesions of the kidney.

Performance evaluation of medical services in nine urban public hospitals based on patient reported experience: a cross-sectional survey

BackgroundThe public hospital reform in China was launched in April 2009. Whether patients are satisfied with medical services or not is an important index to measure the effectiveness of the public hospital reform. We aimed to explore whether patients experience improved medical service under the public hospital reform. MethodsPatient-reported experience measures (PREMs) were used to evaluate medical service performance. We designed a questionnaire to collect patient-reported experiences, using a scoring method based on a scale of one to ten, with one being very poor and ten being excellent. A total of nine urban public hospitals from four provinces (Fujian, Jiangsu, Anhui, and Shanxi) were selected for a field survey in August 2016. We chose two cities as sample sites in each province; one city that had undergone reform and one that had not. In addition, we chose Maanshan city from Anhui province (which underwent public hospital reform well from 2009) as our ‘typical’ sample city. In each city, the biggest general hospital was selected to participate in the study. We ran face-to-face interviews with 2633 patients (we planned to collect data from 200 outpatients and 100 inpatients in each hospital for a sample size 15 times the number of independent variables (20) from nine hospitals. Data were collected from outpatient and emergency patients who had just completed their treatment, inpatients who were being prepared for discharge, or patients who remained in hospital for more than one week. The age of participants was from 0 to 93 (surveys for children under the age of 15 were completed by their parents or guardians), 1199 (45·5%) were male, 1434 (54·5%) were female. We explored factors that might influence performance rating using single-factor analysis of variance and correlation analysis (for example, type of medical insurance, disease diagnosis, disease type, disease severity, and the public hospital reforming policy). FindingsA total of 2633 participants (a minimum of 268 participants from each hospital) were interviewed, including 1703 outpatients (64·68%) and 930 inpatients (35·32%). Overall, the evaluation of medical services was positive. Question relating to the relationship between doctors and patients had the highest score (7·986), whereas the lowest score was given for question relating to medical service quality and effectiveness (4·917). Question relating to medical costs had a lower score (6·882). The total performance scores differed significantly by patient type, age, sex, marital status, educational level, occupation, type of medical insurance, disease diagnosis, disease type, and disease severity. InterpretationThe patient–doctor relationship seems to have improved greatly since the initiation of the public hospital reform, but patients' experience of service quality and efficiency, and medical costs remain unsatisfactory. PREMs could reflect improvements to medical services as a result of the urban public hospital reform, and the public hospital reforming policy might improve the service efficiency and medical costs. FundingThe project is funded by the National Science Foundation of China (number 71473129).

Layer-by-layer assembled gold nanoparticles/lower-generation (Gn≤3) polyamidoamine dendrimers-grafted reduced graphene oxide nanohybrids with 3D fractal architecture for fast, ultra-trace, and label-free electrochemical gene nanobiosensors

Three layer-by-layer (LBL) assembled gold nanoparticles (AuNPs)/lower-generation (Gn≤3) polyamidoamine dendrimer (PD) with reduced graphene oxide (rGO) as the core/mercaptopropinoic acid (MPA)/Au were successfully fabricated and employed as electrochemical gene nanobiosensing platforms with three-dimensional (3D) fractal nanoarchitecture for fast, ultra-trace determination of label-free DNA hybridization. Three Gn≤3PD were initially grafted to graphite oxide (GO) via the covalent functionalization between amino terminals of PD and carboxyl terminals of GO where a concomitant reduction of GO, which were covalently linked onto MPA that was self-assembled onto Au substrate, and finally AuNPs were encapsulated onto GG1PD by strong physicochemical interaction between AuNPs and -OH of rGO in GG1PD, Their morphologies, structures, electrochemical properties, and gene nanobiosensing performances were characterized and evaluated. AuNPs/GG2PD-based probe displayed the best excellent structural stability, lowest mobility on solid surface with the increasing charge resistance, widest linear range (1.1 × 10−6 – 1 × 10−18), and the lowest limit of detection (1.87 × 10−19 M) in comparison with both AuNPs/GG1PD-based and AuNPs/GG3PD-based probes. This work will provide a new candidate for the development of metal nanoparticles functionalized PD with inorganic nonmetallic nanomaterials as cores with 3D fractal nanoarchitecture and promising electrochemical gene nanobiosensing platforms based on dendrimer-nanoinorganic hybrids with 3D nanoarchitectures and LBL assembly for fast and ultra-trace detection of label-free DNA hybridization with potential application in bioanalysis and medical diagnosis of genetic diseases.

Elementary Time Frequency Analysis of EEG Signal Processing

EEG analysis is used as a tool for medical diagnosis of various diseases related to brain like epilepsy, dementia, brain disorders like stress etc. To identify such neural disorders it is essential to process these signal because of the nonstationary behavior. The time frequency analysis of EEG signals provide the correct visualization of EEG signals to extract the various rhythms of frequencies like alpha, beta, gamma waves. The Wavelet transform is used to carry out the time frequency analysis of EEG signal. Wavelets are used to analyze the EEG signals correctly. Their applications include seizure analysis, modeling of neuron potentials etc. To perform these applications it is necessary to perform the mathematical operations on EEG signal by windowing, filtering and then finally reconstruction.

Medical Diagnosis of Chronic Diseases Based on a Novel Computational Intelligence Algorithm

Medical Diagnosis of Chronic Diseases Based on a Novel Computational Intelligence Algorithm

Higher prevalence of nasal polyposis among textile workers: an endoscopic based and controlled study.

There is a deficit of reliable epidemiologic studies exploring the prevalence of Chronic Rhinosinusitis with Nasal Polyps (CRSwNP). Recent data suggests that occupational dust exposure may be involved in its physiopathology. To compare the prevalence of nasal polyposis (NP) in a group of workers with occupational dust exposure (textile workers) and in a control group (retail store workers). Cross-sectional study with a random sample of textile and retail store employees. Clinical data was gathered through a systematic interview, which included RhinoQOL and CAT questionnaires. A systematic endoscopic nasal examination was performed using a 0 degree rigid endoscope. Lund-Kennedy endoscopic score was determined for each participant. Statistical analysis was performed with SPSS. 316 participants were included in the study, i.e. 215 textile workers and 101 retail store workers. NP was found in 19 subjects among textile workers and none in the control group. The prevalence of NP increased by age strata and by years of dust exposition. Polypoid degeneration of the middle turbinate was more prevalent in the exposed group with Lund-Kennedy scoring also higher. RhinoQOL and CAT questionnaires had both significantly higher scores among textile employees. Previous medical diagnosis of atopic diseases or chronic lower airway diseases did not differ between exposed and control groups or even between subjects with and without NP. These results point to an important correlation between occupational dust exposure and NP occurrence.

Heart Disease Diagnosis Using Image Processing By Cuckoo Algorithm before Surgery

Research in Medical & Engineering Sciences Heart Disease Diagnosis Using Image Processing By Cuckoo Algorithm before Surgery Pouya Derakhshan-Barjoei1*, Mojdeh Bahadorzadeh2 and Elham Foroozandeh3 1Department of Telecommunication Engineering, Islamic Azad University, Iran 2Department of General Surgery, Qom University of Medical Sciences, Iran 3Department of Psychology, Islamic Azad University, Iran *Corresponding author: Pouya Derakhshan-Barjoei, Department of Telecommunication Engineering, Naein Branch, Islamic Azad University, Naein, Iran Submission: December 11, 2017; Published: February 13, 2018 DOI: 10.31031/RMES.2018.03.000568 ISSN: 2576-8816Volume3 Issue4

Clinical Decision Support System for Liver Fibrosis Prediction in Hepatitis Patients: A Case Comparison of Two Soft Computing Techniques

Diagnosis of deadly diseases, such as liver fibrosis, is very important. Clinical decision support systems (CDSSs) based on patient’s historical medical data and accurate AI techniques can aid physicians in their decision-making process. The task of arriving at an accurate and timely diagnosis decision is always complex because of the dynamic, vagueness, and uncertainty associated with this disease. Fuzzy logic can perfectly handle these issues. In recent years, two of the most interesting techniques are a fuzzy analytical hierarchy process (FAHP) and an adaptive neuro-fuzzy inference system (ANFIS). The FAHP is popular for dealing with uncertainty in multi-criteria decision-making, and the ANFIS is popular in learning fuzzy inference system from data based on artificial neural networks. To the best of our knowledge, these two methods have not been used to model CDSSs in fibrosis stage detection domain. In this paper, we develop a CDSS based on a case comparison of the effectiveness of the FAHP and the ANFIS in the medical diagnosis of the fibrosis disease. We carefully design and implement two frameworks based on these two techniques. Diagnostic real data of 119 cases infected by chronic viral hepatitis C from the Liver Institute at Mansoura University in Egypt are used to train and test both the FAHP and ANFIS. Criteria and subcriteria weights are based on opinions of two domain experts. The ANFIS model is designed using trial and error based on the analysis of various experiments. Results are later compared with the diagnostic conclusions of medical expert and other three medical and fuzzy techniques. The comparison results show that these two techniques can successfully be employed in designing a diagnostic CDSS system for fibrosis diagnosis. The two techniques achieve a classification accuracy of 93.3%. The results confirm the efficiency and effectiveness of both methods. Therefore, both the FAHP and ANFIS are viable approaches in modeling CDSS for diagnosis of a liver fibrosis stage.

Ultra-Wide mid-IR supercontinuum generation in As2S3 photonic crystal fiber by rods filling technique

In this paper, we study fluid infiltration approach and rod filling technique for dispersion engineering of a photonic crystal fiber (PCF) composed of As2S3-Chalcogenide glass. The numerical results based on finite difference time domain method reveal that when air holes of the innermost ring in a PCF are infiltrated with suitable fluids or filled by glass rods, ultra-flattened near-zero dispersions with high nonlinearities will be achieved over a wide mid-IR wavelength range. The simulations demonstrate that when a 100 fs input optical pulse of 20 kW peak power and central wavelength of 2.5 μm is launched into a 10 mm length of the As2S3 PCF filled by PBG-08 rods, a ripple-free spectral broadening as wide as 9 μm from 1 to 10 μm can be obtained which is used as a suitable source for Mid-IR applications in molecular fingerprint region such as medical diagnosis of diseases, and drug detection.

Full title: peripheral venous catheter complications in children: predisposing factors in a multicenter prospective cohort study

BackgroundPeripheral venous catheterization (PVC) is frequently used in children. This procedure is not free from potential complications. Our purpose was to identify the types and incidences of PVC complications in children and their predisposing factors in a developing country.MethodsWe conducted a prospective observational multicenter study in five pediatric and pediatric surgery departments over a period of 2 months. Two hundred fifteen PVC procedures were conducted in 98 children. The times of insertion and removal and the reasons for termination were noted, and the lifespan was calculated. Descriptive data were expressed as percentages, means, standard deviations, medians and interquartile ranges. The Chi2 test or the Fisher test, with hazard ratios and 95% confidence intervals (CI95%), as well as Student’s t test or the Mann-Whitney U test were used to compare categorical and quantitative variables, respectively, in groups with and without complications. The Spearman test was used to determine correlations between the lifespan and the quantitative variables. The Kruskal Wallis test was used to test for differences in the median lifespan within 3 or more subgroups of a variable. Linear regression and logistic binary regression were used for multivariate analysis. A p-value <0.05 was considered significant.ResultsThe mean lifespan was 68.82 ± 35.71 h. A local complication occurred in 111 PIVC (51.9%) cases. The risk factors identified were a small catheter gauge (24-gauge) (p = 0.023), the use of a volume-controlled burette (p = 0.036), a longer duration of intravenous therapy (p < 0.001), a medical diagnosis of respiratory or infectious disease (p = 0.047), the use of antibiotics (p = 0.005), including cefotaxime (p = 0.024) and vancomycin (p = 0.031), and the use of proton pump inhibitors (p = 0.004).The lifespan of the catheters was reduced with the occurrence of a complication (p < 0.001), including the use of 24-gauge catheters (p = 0.001), the use of an electronic pump or syringe(p = 0.036) and a higher rank of the intravenous device in each patient (p = 0.010).ConclusionsPVC complications were frequent in our pediatric departments and are often associated with misuse of the device. These results could engender awareness among both doctors and nurses regarding the need for rationalization of the use of PVC and better adherence to the recommendations for the use of each drug and each administration method.

A FAST CORRELATION FILTER BASED GRADIENT BOOSTING CLASSIFIER FOR DISEASE DIAGNOSIS

Disease diagnosis is the process to find the disease with specified details of a person's symptoms. Diagnosing the Disease is time consuming due to the need to analyze relevant microorganisms. Due to large growth in world’s population, Classification model receives a great deal in any domain of research and also a consistent tool for medical disease diagnosis. The domain of classification approach is used in the disease diagnosis, disease prediction, bio informatics and so on. However, an effective disease diagnosis model and the accuracy with the disease prediction were compromised. In order to obtain higher classification accuracy for heart and stroke disease diagnosis, a Fast Correlation Filter based Gradient Boosting Classifier (FCF GBC) technique is introduced. The main objective of the FCF-GBC technique is effectively performs disease diagnosis with two processing steps. Initially, Fast Correlation Filtering (FCF) algorithm is used to select the most relevant attributes (i.e. features) for disease diagnosis and filter out the irrelevant attributes in dataset. FCF uses symmetrical uncertainty to calculate the dependences of attributes and discovers the relevant attributes. After that, A Gradient Boosting Classifier is used for classifying and predicting the heart and stroke disease from the extracted attributes. Experimental evaluation is carried out using Statlog heart disease dataset and International Stroke Trial Database on the factors such as classification accuracy, classification time, error rate and true positive rate with respect to number of patients.

Inventory survey and influence factor analysis on the sleep quality of cervical cancer patients

Objective To understand about the sleep quality of cervical cancer patients, investigate the correlative factors that influence sleep quality, so as to provide the basis for improving the sleep quality of cervical cancer patients. Methods Cervical cancer patients whose postoperative tissue pathology was diagnosed as FIGO stage I and II were selected.7 days before and after operation, 1 month after operation in the follow-up visit (3 times), demographic questionnaire form, PSQI, CES-D self-rating depression scale, POMS-SF self-rating anxiety scale and cancer therapy function questionnaire (FACT-G) were used to have investigation and analysis on cervical cancer patients and hospitalized benign tumor (uterine fibroid) patients in the same term. Results Cervical cancer patients had no statistical difference from uterine fibroid patients on demographic questionnaire form.In different stages, PSQI aggregate score, CES-D depression, POMS-SF anxiety and FACT-G scores to the cervical cancer patients 7 days before and after operations, follow-up visit 1 month after operation had no significant statistical difference. However, compared with uterine fibroid patients, PSQI aggregate score, CES-D depression, POMS-SF anxiety and FACT-G scores of cervical cancer patients were higher 7 days before and after operations, follow-up visit 1 month after operation.However, the living quality score of FACT-G was lower than uterine fibroid patients, and the difference had statistical significance. Multivariate Logistic regression analysis indicated that marital status, educational level, working condition, family economic status, medical payment method, disease diagnosis and staging, pain score, depression, anxiety and living quality were obviously associated with the sleep disorder of cervical cancer patients. Conclusion The sleep quality of cervical cancer patients in different stages before operation and in the early stage after operation was inferior to benign tumor patients.In addition, sleep disorder occurrence rate of cervical cancer patients is higher.Sleep disorder can not only result in depression and anxiety easily, but also influence the living quality of patients. Key words: Cervical cancer; Sleep quality; Sleep disturbance

Early readmission in a high complexity public hospital in cardiology

Objective: to evaluate the early readmission of patients in a high complexity public hospital in cardiology. Methods: this is a descriptive, documental and retrospective study, carried out in a public hospital. Results: in 2012, 729 of the 9,218 hospitalized patients were readmitted, 47.9% of them were readmitted within 30 days after discharge, 61% were men, with a mean age of 57 years old, with the main medical diagnosis of heart disease (heart failure, treatment of acute coronary syndrome, among others) on admission (44.7%) and readmission (45.8%). Most were readmitted for the same medical reason that led to their first hospitalization. Conclusion: considering the profile of the population admitted and readmitted to the institution, it is believed that the rate of readmission is mainly due to the profile of the patients, considering the high prevalence of non-communicable chronic diseases, and coronary artery disease considered unapproachable for percutaneous or surgical when hospitalized.

A non-enzymatic glucose sensor based on NiO nanoparticles/functionalized SBA 15/MWCNT-modified carbon paste electrode

A simple non-enzymatic glucose sensor was proposed based on electrodeposited NiO nanoparticles (NiO NPs) onto a functionalized Santa Barbara Amorphous (SBA 15) material/multiwall carbon nanotube (MWCNTs)-modified carbon paste electrode (CPE). NiO NPs deposited on the modified electrode showed good catalytic activities toward glucose oxidation in alkaline media. Scanning electron microscopy (SEM) studies demonstrated that large amounts of NiO nanoparticles can be deposited on the surface of the modified electrode. In addition, NiO NPs/functionalized SBA 15/MWCNT-modified CPE was also characterized by electrochemical methods including cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS). The amperometric signals were linearly proportional to glucose concentration in the range of 0.06–400 μM with a detection limit of 0.023 μM, which was comparable with previously reported glucose sensors. Moreover, the modified CPE was successfully applied for the detection of glucose in real samples. The disposable amperometric sensor in this study showed a rapid and highly sensitive response to glucose which might find promising applications in medical applications and disease diagnosis.

Developing obstetric medicine training in Latin America.

Maternal mortality is an important indicator of health in populations around the world. The distribution of maternal mortality ratio globally shows that middle- and low-income countries have ∼99% of the mortality burden. Most countries of Latin America are considered to be middle- or low-income countries, as well as areas of major inequities among the different social classes. Medical problems in pregnancy remain an important cause of morbidity and mortality in this region. Previous data indicate the need for a call to action for adequate diagnosis and care of medical diseases in obstetric care. The impact of nonobstetric and medical pathologies on maternal mortality in Latin America is largely unknown. In Latin America, two educational initiatives have been proposed to improve skills in maternity care. The Advanced Life Support in Obstetrics (ALSO®) was first started to address obstetric emergencies, and subsequently adapted for low-middle-income country settings as the Global ALSO®. In parallel, the Latin American obstetric anesthesia community has progressively focused on improvement of several intrapartum/intraoperative issues, which has secondarily taken them to embrace the obstetric medicine area on interest and join the former initiatives. In the present review, we summarize the available data regarding medical morbidity and mortality in pregnancy in Latin America, as well as the challenges, achievements, issues, initiatives, and future directions encouraging maternal health educators, health care trainers, and physicians in middle- and low-income countries, such as many Latin American ones, to improve and/or change attitudes, if needed, on current clinical practice.