Materiały źródłowe

• #1 Approach to the child with acute diarrhea in resource-limited settings – UpToDate

  https://www.uptodate.com/contents/approach-to-the-child-with-acute-diarrhea-in-resource-limited-settings

  Diarrhea refers to passage of loose or watery stools at least three times in a 24-hour period. Diarrheal illness is an important cause of child mortality; among children <5 years of age worldwide, it caused over 480,000 estimated deaths in 2019. [...] In resource-limited settings, infants experience a median of six episodes annually, and children experience a median of three episodes annually. There is considerable geographic variability in the incidence and associated mortality of diarrheal illnesses; certain regions may need targeted interventions to improve these outcomes. [...] The mortality of children with diarrhea and severe malnutrition may exceed 50 percent. In severely malnourished patients, important clinical signs of dehydration may be masked by kwashiorkor and sepsis. [...] Clinical manifestations and complications of acute diarrhea include dehydration, electrolyte disturbances, and malnutrition. Manifestations of central nervous system (CNS) involvement may include seizures and encephalopathy.

• #2 Approach to the child with acute diarrhea in resource-limited settings – UpToDate

  https://www.uptodate.com/contents/approach-to-the-child-with-acute-diarrhea-in-resource-limited-countries

  Diarrhea refers to passage of loose or watery stools at least three times in a 24-hour period. Diarrheal illness is an important cause of child mortality; among children <5 years of age worldwide, it caused over 480,000 estimated deaths in 2019. [...] In resource-limited settings, infants experience a median of six episodes annually, and children experience a median of three episodes annually. There is considerable geographic variability in the incidence and associated mortality of diarrheal illnesses; certain regions may need targeted interventions to improve these outcomes. [...] The mortality of children with diarrhea and severe malnutrition may exceed 50 percent. In severely malnourished patients, important clinical signs of dehydration may be masked by kwashiorkor and sepsis. [...] Clinical manifestations and complications of acute diarrhea include dehydration, electrolyte disturbances, and malnutrition. Manifestations of central nervous system (CNS) involvement may include seizures and encephalopathy.

• #3 Exploring Machine Learning Algorithms to Predict Diarrhea Disease and Identify its Determinants among Under-Five Years Children in East Africa

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11442874/

  The second most common cause of death for children under five is diarrhea. Early Predicting diarrhea disease and identify its determinants (factors) using an advanced machine learning model is the most effective way to save the lives of children. Hence, this study aimed to predict diarrheal diseases, identify their determinants, and generate some rules using machine learning models. […] The final experimentation results indicated the random forest model performed the best to predict diarrhea disease with an accuracy of 86.5%, precision of 89%, F-measure of 86%, AUC curve of 92%, and recall of 82%. Important predictors identified age, countries, wealth status, mothers educational status, mothers age, source of drinking water, number of under-five children immunization status, media exposure, timing of breast feeding, mothers working status, types of toilet, and twin status were associated with a higher predicted probability of diarrhea disease.

• #4

  https://link.springer.com/article/10.1007/s44197-024-00259-9

  The second most common cause of death for children under five is diarrhea. Early Predicting diarrhea disease and identify its determinants (factors) using an advanced machine learning model is the most effective way to save the lives of children. Hence, this study aimed to predict diarrheal diseases, identify their determinants, and generate some rules using machine learning models. […] The final experimentation results indicated the random forest model performed the best to predict diarrhea disease with an accuracy of 86.5%, precision of 89%, F-measure of 86%, AUC curve of 92%, and recall of 82%. Important predictors identified age, countries, wealth status, mothers educational status, mothers age, source of drinking water, number of under-five children immunization status, media exposure, timing of breast feeding, mothers working status, types of toilet, and twin status were associated with a higher predicted probability of diarrhea disease.

• #5 Exploring Machine Learning Algorithms to Predict Diarrhea Disease and Identify its Determinants among Under-Five Years Children in East Africa

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11442874/

  According to this study, child caregivers are fully aware of sanitation and feeding their children, and moms are educated, which can reduce child mortality by diarrhea in children in east Africa. This leads to a recommendation for policy direction to reduce infant mortality in East Africa. […] The study compared four different supervised machine learning classification methods to verify the superiority of one of the proposed methods. The diarrhea disease status outcome prediction of Random Forest, Decision Tree (DT), GB (Gradient Boosting), K-Nearest Neighbor, and Logistic Regression experiments were done with the same testing parameters. Since accuracy, AUC, precision, recall, and F-measure are the parameters used to evaluate the performance of the model, and since RF performs the best overall in the proposed model, it was chosen as the top machine-learning algorithm. The outcomes are displayed in (Fig. 4), (Fig. 5), and (Table 3). With an accuracy of 86.5%, precision of 89%, F-measure of 86%, AUC curve of 92%, and recall of 82%, random forest is the best classifier in this study.

• #6

  https://link.springer.com/article/10.1007/s44197-024-00259-9

  According to this study, child caregivers are fully aware of sanitation and feeding their children, and moms are educated, which can reduce child mortality by diarrhea in children in east Africa. This leads to a recommendation for policy direction to reduce infant mortality in East Africa. […] The study compared four different supervised machine learning classification methods to verify the superiority of one of the proposed methods. The diarrhea disease status outcome prediction of Random Forest, Decision Tree (DT), GB (Gradient Boosting), K-Nearest Neighbor, and Logistic Regression experiments were done with the same testing parameters. Since accuracy, AUC, precision, recall, and F-measure are the parameters used to evaluate the performance of the model, and since RF performs the best overall in the proposed model, it was chosen as the top machine-learning algorithm. The outcomes are displayed in (Fig. 4), (Fig. 5), and (Table 3). With an accuracy of 86.5%, precision of 89%, F-measure of 86%, AUC curve of 92.7%, and recall of 82%, random forest is the best classifier in this study.

• #7 Exploring Machine Learning Algorithms to Predict Diarrhea Disease and Identify its Determinants among Under-Five Years Children in East Africa

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11442874/

  Machine learning approaches can be used to classify certain hidden information that is indiscernible using conventional statistical tools. The findings of the last experiment showed that the gradient boosting model was the most accurate at evaluating risk factors and predicting diarrhea disease among children under five. The important determinants selected by Gradient Boosting were children age, countries, wealth status, mothers educational status, mother age, source of drinking water, number of under-five children immunization status, media exposure, timing of breast feeding, mothers working status, types of toilets, and twin status. Policymakers should consider the researchs findings and develop a plan for decreasing child mortality by diarrhea disease in east African nations based on the variables that have been found to be significant.

• #8

  https://link.springer.com/article/10.1007/s44197-024-00259-9

  The important determinants selected by Gradient Boosting were children age, countries, wealth status, mothers educational status, mother age, source of drinking water, number of under-five children immunization status, media exposure, timing of breast feeding, mothers working status, types of toilets, and twin status. Policymakers should consider the researchs findings and develop a plan for decreasing child mortality by diarrhea disease in east African nations based on the variables that have been found to be significant.

• #9 Clinical predictors for etiology of acute diarrhea in children in resource-limited settings

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7588112/

  Our findings can be used by doctors to guide the appropriate use of antibiotics for diarrhea in children. […] Using machine learning algorithms, we found that a model with just 5 variables (age, season, HAZ, bloody diarrhea, and vomiting), could accurately predict viral etiology, with a cross-validated AUC of 0.825. […] The most significant predictors for differentiating viral from other etiologies were: age, HAZ, season, bloody diarrhea, and vomiting. […] Our prediction model showed that for predicting a viral etiology, for a desired specificity of 0.85, we achieved a sensitivity of 0.59.

• #10 Clinical predictors for etiology of acute diarrhea in children in resource-limited settings | PLOS Neglected Tropical Diseases

  https://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0008677

  Our findings can be used by doctors to guide the appropriate use of antibiotics for diarrhea in children. […] Using machine learning algorithms, we found that a model with just 5 variables (age, season, HAZ, bloody diarrhea, and vomiting), could accurately predict viral etiology, with a cross-validated AUC of 0.825. […] Our prediction model showed that for predicting a viral etiology, for a desired specificity of 0.85, we achieved a sensitivity of 0.59. […] The most significant predictors for differentiating viral from other etiologies were: age, HAZ, season, bloody diarrhea, and vomiting. […] Given that GEMS was conducted in 7 countries across Africa and Asia, we examined the model performance across sites. […] Our study has a number of limitations. […] In conclusion, utilizing a large number of cases and quantitative molecular methods of pathogen detection with etiologic attribution based on a case-control study, we showed that etiology prediction could be attained for episodes of acute diarrhea with as few as 5 variables.

• #11 Clinical predictors for etiology of acute diarrhea in children in resource-limited settings

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7588112/

  Diarrhea is one of the leading causes of childhood morbidity and mortality in lower- and middle-income countries. […] Clinical predictors are a potential non-laboratory method to more accurately assess diarrheal etiology, the knowledge of which could improve management of pediatric diarrhea. […] Predictors of the etiology of pediatric diarrhea can be used by providers in low-resource settings to inform clinical decision-making. […] The use of non-laboratory methods to diagnose viral causes of diarrhea could be a step towards reducing inappropriate antibiotic prescription worldwide. […] Using clinical information to predict which cases are caused by viruses, and thus wouldn’t need antibiotics, would help to improve appropriate use of antibiotics. […] We found that a lower age, dry and cold season, nutritional status defined by increased height, lack of blood diarrhea, and vomiting, were the clinical factors most predictive of whether the diarrhea was caused by a virus.

• #12 Clinical predictors for etiology of acute diarrhea in children in resource-limited settings | medRxiv

  https://www.medrxiv.org/content/10.1101/2020.01.27.20016725v2.full-text

  Diarrhea is one of the leading causes of childhood morbidity and mortality in lower- and middle-income countries. […] Predictors of the etiology of pediatric diarrhea can be used by providers in low-resources setting to inform clinical decision-making. […] Using clinical information to predict which cases are caused by viruses, and thus wouldn’t need antibiotics, would help to improve appropriate use of antibiotics. […] We found that a lower age, dry and cold season, nutritional status defined by increased height, lack of blood diarrhea, and vomiting, were the clinical factors most predictive of whether the diarrhea was caused by a virus. […] Our findings can be used by doctors to guide the appropriate use of antibiotics for diarrhea in children. […] Using machine learning algorithms, we found that a model with just 5 variables (age, season, HAZ, bloody diarrhea, and vomiting), could accurately predict viral etiology, with a cross-validated AUC of 0.825.

• #13 Clinical predictors for etiology of acute diarrhea in children in resource-limited settings | medRxiv

  https://www.medrxiv.org/content/10.1101/2020.01.27.20016725v2.full-text

  Our prediction model showed that for predicting a viral etiology, for a desired specificity of 0.85, we achieved a sensitivity of 0.59. […] The most significant predictors for differentiating viral from other etiologies were: age, HAZ, season, bloody diarrhea, and vomiting. […] Given that GEMS was conducted in 7 countries across Africa and Asia, we examined the model performance across sites. […] Our study has a number of limitations. […] Our findings confirm previously considered predictors of viral etiology including lack of bloody diarrhea, vomiting, younger age, and a dry and cool climate, and reveal additional predictors of viral etiology associated with anthropometric measures.

• #14 Derivation and validation of a clinical predictive model for longer duration diarrhea among pediatric patients in Kenya using machine learning algorithms | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-025-02855-6

  Despite the adverse health outcomes associated with longer duration diarrhea (LDD), there are currently no clinical decision tools for timely identification and better management of children with increased risk. […] Our study suggests ML derived algorithms could be used to rapidly identify children at increased risk of LDD. Integrating ML derived models into clinical decision-making may allow clinicians to target these children with closer observation and enhanced management. […] A systematic review of predictive modeling for diarrhea in pediatric populations, encompassing 38 studies, identified that the most common research topics were disease forecasts, vaccine-related predictions, and disease/pathogen detection with machine learning (ML) as the primary modelling technique. […] Developing a highly sensitive model that utilizes socio-demographic and clinical characteristics of patients could facilitate the timely identification of children at heightened risk of LDD by clinicians, enabling better, timelier care and close monitoring potentially improving outcomes among this vulnerable group of children.

• #15 Derivation and validation of a clinical predictive model for longer duration diarrhea among pediatric patients in Kenya using machine learning algorithms | BMC Medical Informatics and Decision Making | Full Text

  https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-025-02855-6

  Our study shows the practical utility of machine learning algorithms in rapid identification of children at increased risk of LDD in our setting. The use of our validated RF model in clinical settings to complement clinician judgement could help to prioritize resources at high-risk children and ensure close monitoring and better management while allowing low-risk children return home earlier.

• #16 Derivation and external validation of a clinical prognostic model identifying children at risk of death following presentation for diarrheal care | PLOS Global Public Health

  https://journals.plos.org/globalpublichealth/article?id=10.1371/journal.pgph.0001937

  Diarrhea continues to be a leading cause of death for children under-five. Amongst children treated for acute diarrhea, mortality risk remains elevated during and after acute medical management. Identification of those at highest risk would enable better targeting of interventions, but available prognostic tools lack validation. […] Our findings suggest it is possible to identify children most likely to die after presenting to care for acute diarrhea. This could represent a novel and cost-effective way to target resources for the prevention of childhood mortality. […] We used a combination of machine learning and conventional regression methods to derive and externally validate clinical prognostic models for death following acute diarrhea. Our CPM to predict death in community-dwelling children at the time they present for care for acute MSD had good discriminative ability in the derivation dataset (GEMS AUC = 0.84, 95% CI: 0.82, 0.86) as well as at external validation (Kilifi AUC = 0.74, 95% CI: 0.71, 0.77). […] Our CPM is promising as a screening tool to identify children likely to die after presentation, and therefore who may benefit from more intensive care and follow-up.

• #17 Immune-checkpoint inhibitor-induced diarrhea and colitis in patients with advanced malignancies: retrospective review at MD Anderson | Journal for ImmunoTherapy of Cancer

  https://jitc.bmj.com/content/6/1/37

  Diarrhea was recorded in 117 (36%) patients; 79 (24%) of them required immunosuppressive treatment of either systemic corticosteroid without infliximab (n =44) or with infliximab (n =35). […] Patients who required immunosuppressants had better overall survival than those who did not require treatment for colitis or diarrhea (P 0.001). […] Diarrhea was an independent predictor of a favorable overall survival (P 0.001), irrespective of treatment need (P =0.003). […] Patients with ICPI-induced diarrhea or colitis have improved survival outcomes. […] Diarrhea is an independent predictor of an improved survival regardless of treatment requirement. […] Immunosuppressive treatment for diarrhea did not significantly affect overall survival, however, infection rates were numerically higher among patients who received steroids for a long duration. Therefore, early non-steroid immunosuppressive therapy may ensure a more favorable overall outcome.

• #18

  https://link.springer.com/article/10.1007/s10549-014-3126-0

  Lapatinib and capecitabine (L-CAP) is effective in HER-2 positive patients with metastatic breast cancer (MBC). However, moderate to severe diarrhea and rash (grade 2) are problematic dose limiting toxicities. […] Patient age, presence of skin metastases at baseline, treatment being initiated in the spring, earlier cycles, and grade I diarrhea in the prior cycle were identified as being significant predictors for grade 2 diarrhea. […] The ROC analysis indicated good predictive accuracy for the diarrhea algorithm with an area under the curve of 0.78 (95 %CI: 0.720.82). […] Prior to each cycle of therapy, patients with risk scores 125 units would be considered at high risk for developing grade 2 diarrhea. […] Our models provide patient-specific risk information that could be helpful in assessing the risks and benefits of L-CAP in the MBC patients.

• #19 A prediction model of enteral nutrition complicated with severe diarrhea in ICU patients based on CD55 – Xie – Annals of Palliative Medicine

  https://apm.amegroups.org/article/view/56113/html

  Severe diarrhea is a common complication of enteral nutrition in intensive care unit (ICU) patients. […] We intended to build a prediction model of enteral nutrition complicated with severe diarrhea in ICU patients based on CD55. […] The prediction model of enteral nutrition complicated with severe diarrhea in ICU patients was constructed through data processing analysis. […] gCD55 and eCD55 had certain predictive value in enteral nutrition complicated with severe diarrhea. […] The decrease of gCD55 and eCD55 had certain predictive value in enteral nutrition complicated with diarrhea. The model established by combining gCD55, eCD55 and IL-10 showed a good degree of calibration and differentiation. It provided reference value for early detection of severe diarrhea.

• #20

  https://link.springer.com/article/10.1007/s10549-014-3126-0

  Diarrhea and rash are frequent AEs to agents targeting HER1 and 2. Our study describes the development of predictive models and scoring algorithms for grade 2 (moderate to severe) diarrhea and skin rash in advanced stage HER-2 positive breast cancer patients receiving lapatinib and capecitabine. […] The ability to preempt these episodes with the use of validated mathematical algorithms will improve patient quality of life, reduce pain, and suffering and avoid unnecessary health care expenditures. […] The external validation and eventual clinical application of these prediction tools will be an important source of patient-specific risk information for the practicing oncologist and can enhance patient care by utilizing preventative strategies in a proactive manner.

• #21 Frontiers | Inherited transthyretin cardiac amyloidosis presenting with diastolic heart failure and gastrointestinal symptoms: a case report and literature review

  https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2025.1588291/full

  The prevalence of Inherited transthyretin cardiac amyloidosis (hATTR-CA) is rising with an aging population and more mutation carriers. […] Patients are often diagnosed late, leading to refractory heart failure and a poor prognosis. […] With early diagnosis and active treatment, the patient’s prognosis improved, symptoms of heart failure were controlled, and quality of life significantly improved. […] This case emphasizes the importance of early diagnosis and accurate treatment of hATTR-CA, particularly the role of imaging in diagnosing myocardial infiltration. […] Timely identification of CA allows for effective treatment, improving prognosis. […] Delayed diagnosis worsens the prognosis. […] This is seen in 1% of primary systemic amyloidosis cases. Delayed diagnosis worsens the prognosis. […] By leveraging multidisciplinary collaboration and advanced diagnostic tools, timely recognition and appropriate treatment can be initiated, significantly improving the patient’s quality of life.

• #22 Prediction of Childhood Diarrhea in Bangladesh using Machine Learning Approach

  https://scholars.direct/Articles/biomedical-research/ibr-4-021.php?jid=biomedical-research

  This study allows policy makers towards appropriate decisions to reduce childhood diarrhea in Bangladesh. […] Our findings show that child’s age has the significant impact on diarrhea. It is observed that the children who ages are 12-23 and 24-59 moths have the lower prevalence of diarrhea. […] Our study shows that SVM with RBF gives better performance scores compared to others. […] This study investigate the risk factors of childhood diarrhea and also suggests a prediction model to predict childhood diarrhea. This shows that child age, mother’s education, region and wealth index are significant impact on childhood diarrhea. In this study, LDA, QDA, NB, and SVM-based classifiers are used to predict the childhood diarrhea status. SVM with radial basis kernel gives better performance compared to others.

• #23 Prediction of Childhood Diarrhea in Bangladesh using Machine Learning Approach

  https://scholars.direct/Articles/biomedical-research/ibr-4-021.php?jid=biomedical-research

  Diarrhea has remained a major health problem among under-five (U5) children that leads high level of morbidity and mortality. The objective of this study is to determine the socio-demographic risk factors of diarrhea as well as predict of diarrhea status using machine learning (ML) based approach among U5 children in Bangladesh. […] Logistic regression (LR) is used to determine the high-risk factors of diarrhea. Then four ML-based approach namely naïve Bayes (NB), linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM) was applied to predict the child’s diarrhea status and accuracy, sensitivity, and specificity are used to evaluate the performance of these classifiers. […] LR model showed that the child’s age, region (Khulna and Rangpur), mothers who had completed secondary education, and respondents who were rich wealth index, significantly associated risk factors for diarrhea disease. Our findings indicate that SVM with radial basis kernel yielded 65.61% accuracy, 66.27% sensitivity, and 52.28% specificity which are comparatively better than others.

Zobacz więcej