Kolka niemowlęca – Rokowania, prognozy i postęp choroby

Kolka niemowlęca
Rokowania, prognozy i postęp choroby

Kolka niemowlęca definiowana jest jako nadmierny płacz w pierwszych 3 miesiącach życia, natomiast u koni termin ten odnosi się do ostrego bólu brzucha, stanowiącego częsty stan nagły w weterynarii. W celu poprawy prognozy przeżycia koni z kolką opracowano system oceny oparty na sześciu kluczowych parametrach klinicznych, w tym częstości akcji serca, stanie błon śluzowych oraz hematokrycie (PCV). Zakres oceny wynosi od 0 do 12, gdzie wynik ≥7 wskazuje na wysokie ryzyko zgonu, z czułością 86%, swoistością 64%, dodatnią wartością predykcyjną 88% i ujemną 57%. W przypadku leczenia zachowawczego hematokryt był jedynym istotnym predyktorem, natomiast w leczeniu chirurgicznym kluczowe były częstość akcji serca i nieprawidłowe błony śluzowe. Analiza płynu z jamy brzusznej, zwłaszcza jego kolor i ciężar właściwy, dostarcza dodatkowych informacji prognostycznych, choć nie powinna być stosowana jako jedyny wskaźnik do podejmowania decyzji terapeutycznych.

Kolka niemowlęca – prognoza i przewidywanie wyników leczenia

Systemy oceny prognostycznej w kolce
Czynniki prognostyczne w kolce
Skuteczność systemów oceny prognostycznej
Analiza płynów jamy brzusznej w prognozowaniu
Sztuczna inteligencja w prognozowaniu wyników kolki
Długoterminowe rokowanie kolki niemowlęcej

Znaczenie rozwoju systemów oceny kolki dla praktyki klinicznej

Kolejne rozdziały

Kolka niemowlęca – prognoza i przewidywanie wyników leczenia

Kolka niemowlęca (Colic) to stan często definiowany jako nadmierna ilość płaczu w pierwszych 3 miesiącach życia dziecka¹. U koni natomiast określenie to odnosi się do ostrego bólu brzucha, który jest częstym stanem nagłym w praktyce weterynaryjnej. Ze względu na różnorodność etiologii, przewidywanie przeżycia stanowi wyzwanie zarówno w przypadku niemowląt, jak i zwierząt²³.

Systemy oceny prognostycznej w kolce

W celu lepszej prognozy wyników leczenia kolki opracowano różne systemy oceny. W przypadku koni, przeprowadzono retrospektywne wieloośrodkowe badanie kliniczne, aby określić parametry kliniczne związane z przeżyciem koni z kolką i wykorzystać je do opracowania systemu oceny przeżycia kolki⁴. System ten został następnie zwalidowany przy użyciu danych klinicznych w prospektywnej części badania⁵.

Czynniki prognostyczne w kolce

W badaniach nad kolką u koni zidentyfikowano szereg zmiennych związanych z przewidywaniem przeżycia. Spośród 28 badanych parametrów, sześć zostało włączonych do systemu oceny kolki⁶. Tradycyjne zmienne, takie jak częstość akcji serca, błony śluzowe i hematokryt (PCV) okazały się najważniejszymi predyktorami wyniku u hospitalizowanych przypadków kolki⁷.

W przypadku kolki leczonej zachowawczo, hematokryt był jedynym istotnym predyktorem, natomiast w przypadkach leczonych chirurgicznie istotnymi predyktorami były częstość akcji serca i nieprawidłowe błony śluzowe⁸.

Skuteczność systemów oceny prognostycznej

Całkowity zakres oceny kolki wynosił od 0 do 12, przy czym najwyższy wynik oznaczał najniższe prawdopodobieństwo przeżycia. Optymalna wartość graniczna do przewidywania przeżycia wynosiła siedem, co dawało 86% czułość i 64% swoistość, z dodatnią wartością predykcyjną 88% i ujemną wartością predykcyjną 57%⁹¹⁰.

Konie z prospektywnej części badania, które otrzymały wynik ≥7, zostały sklasyfikowane jako przewidywane do zgonu, a te z wynikiem <7 przewidywane do przeżycia. W porównaniu z rzeczywistym wynikiem czułość, swoistość, dodatnia i ujemna wartość predykcyjna systemu oceny kolki wynosiły odpowiednio 84%, 62%, 88% i 52%¹¹¹².

Analiza płynów jamy brzusznej w prognozowaniu

Badania wykazały, że analiza płynu z jamy brzusznej może dostarczyć klinicznie użytecznych informacji dotyczących prognozy. Kolor płynu jamy brzusznej i ciężar właściwy miały wysoką dodatnią wartość predykcyjną dla typu zmiany chorobowej, a wiek pacjenta i kolor płynu jamy brzusznej miały wysoką dodatnią wartość predykcyjną dla wyniku leczenia pacjenta¹³.

Konie z ciemniejszym płynem częściej miały gorsze długoterminowe rokowanie. Jednakże badacze zalecają ostrożność, ponieważ sam płyn z jamy brzusznej nie może być wiarygodnie wykorzystywany do przewidywania rodzaju leczenia, rodzaju zmiany chorobowej lub wyniku, choć może dostarczyć ważnych, istotnych klinicznie informacji¹⁴.

Sztuczna inteligencja w prognozowaniu wyników kolki

Nowsze podejścia do przewidywania wyników kolki obejmują wykorzystanie uczenia maszynowego i wytłumaczalnej sztucznej inteligencji (XAI). Badania integrujące te technologie wykorzystują dane kliniczne, proceduralne i diagnostyczne do przewidywania wyników przeżycia koni z kolką¹⁵.

Metody takie jak SHAP (Shapley additive explanations) przekształcają modele „czarnej skrzynki” w interpretowalne ramy, które mogą pomóc w zrozumieniu czynników determinujących przeżycie, umożliwiając ukierunkowane i oparte na dowodach interwencje¹⁶¹⁷.

Projekty uczenia maszynowego mają na celu przewidywanie prawdopodobieństwa przeżycia koni z kolką poprzez opracowywanie modeli predykcyjnych z wykorzystaniem historycznych danych medycznych. Modele te oceniają różne stany medyczne i cechy, aby określić prawdopodobieństwo przeżycia¹⁸.

Długoterminowe rokowanie kolki niemowlęcej

W przypadku kolki niemowlęcej, długoterminowe obserwacje wykazały, że nie ma różnicy między grupami w odniesieniu do internalizacji problemów behawioralnych, a także percepcji rodziców dotyczącej płaczu, karmienia, snu i funkcjonowania rodziny¹⁹.

Badania wydają się wykazywać, że kolka niemowlęca nie prowadzi do długoterminowych trudności behawioralnych, sugerując jednocześnie, że stosowanie probiotyków w okresie niemowlęcym nie przynosi korzyści w późniejszym zachowaniu dziecka²⁰.

Znaczenie rozwoju systemów oceny kolki dla praktyki klinicznej

Opracowanie i walidacja systemu oceny kolki może pomóc specjalistom weterynaryjnym w przewidywaniu wyników przeżycia koni z ostrym bólem brzucha. Wyniki walidacji pokazują, że taki system oceny może rzeczywiście zapewnić wiarygodne oszacowanie prawdopodobieństwa przeżycia, wspierając jego potencjalne zastosowanie w praktykach weterynaryjnych²¹.

Dokładne przewidywanie występowania kolki może pomóc lekarzom weterynarii i właścicielom podejmować świadome decyzje w celu poprawy leczenia i opieki²². Personalizowane informacje uzyskane za pomocą SHAP stanowią najbardziej transformacyjne odkrycie w badaniach nad wykorzystaniem sztucznej inteligencji w zarządzaniu kolką²³.

Dzięki połączeniu globalnych i lokalnych wyjaśnień, SHAP zapewnia solidne ramy do zrozumienia determinantów przeżycia, umożliwiając ukierunkowane i oparte na dowodach interwencje²⁴.

Kolejne rozdziały

Zapraszamy do dalszego czytania naszego leksykonu.

Wybierz kolejny rozdział z menu poniżej, aby otworzyć nową podstronę kompedium wiedzy i uzyskać szczegółowe informację o leku, substancji lub chorobie.

Materiały źródłowe

#1 Do Risk Factors During Infancy Predict Eosinophilic Esophagitis – Practical Gastro
https://practicalgastro.com/2019/01/19/do-risk-factors-during-infancy-predict-eosinophilic-esophagitis/
Infant colic is typically defined as excessive amounts of crying in the first 3 months of life. […] It is also unclear as to the long-term outcome of infants with colic. […] Long-term follow up demonstrated that there was no difference between groups in regards to internalizing behavioral problems as well as parental perceptions of crying, feeding, sleeping, and family function. […] This study appears to demonstrate that infant colic does not lead to long-term behavioral difficulties and suggests that probiotic use during infancy has no benefit in later childhood behavior.
#2 Development of a Colic Scoring System to Predict Outcome in Horses – PubMed
https://pubmed.ncbi.nlm.nih.gov/34692803/
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. A retrospective, multi-institutional clinical study was performed to determine clinical parameters associated with survival of horses with colic, and to use them to develop a colic survival scoring system. The scoring system was then validated using clinical data in the prospective portion of the study. Medical records from 67 horses presenting for acute abdominal pain were evaluated to develop the colic assessment score. Twenty eight variables were compared between survivors and non-survivors and entered into logistic regression models for survival. Of these, six variables were included in the colic assessment score. A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%.
#3 Development of a Colic Scoring System to Predict Outcome in Horses. | Research Bank
https://madbarn.com/research/development-of-a-colic-scoring-system-to-predict-outcome-in-horses/?srsltid=AfmBOorunK0bHhJkiKVsZhkbUYqPmhjMohP0oslcd1NOhvvoeymegPzu
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. […] The scoring system was then validated using clinical data in the prospective portion of the study. […] A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%. […] Horses from the prospective portion of the study that received a score 7 were classified as predicted to die and those with a score 7 were predicted to survive. […] The classification was compared to the actual outcome, of which the sensitivity, specificity, positive and negative predictive values of the colic assessment score were 84, 62, 88, and 52%, respectively.
#4 Development of a Colic Scoring System to Predict Outcome in Horses – PubMed
https://pubmed.ncbi.nlm.nih.gov/34692803/
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. A retrospective, multi-institutional clinical study was performed to determine clinical parameters associated with survival of horses with colic, and to use them to develop a colic survival scoring system. The scoring system was then validated using clinical data in the prospective portion of the study. Medical records from 67 horses presenting for acute abdominal pain were evaluated to develop the colic assessment score. Twenty eight variables were compared between survivors and non-survivors and entered into logistic regression models for survival. Of these, six variables were included in the colic assessment score. A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%.
#5 Development of a Colic Scoring System to Predict Outcome in Horses. | Research Bank
https://madbarn.com/research/development-of-a-colic-scoring-system-to-predict-outcome-in-horses/?srsltid=AfmBOorunK0bHhJkiKVsZhkbUYqPmhjMohP0oslcd1NOhvvoeymegPzu
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. […] The scoring system was then validated using clinical data in the prospective portion of the study. […] A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%. […] Horses from the prospective portion of the study that received a score 7 were classified as predicted to die and those with a score 7 were predicted to survive. […] The classification was compared to the actual outcome, of which the sensitivity, specificity, positive and negative predictive values of the colic assessment score were 84, 62, 88, and 52%, respectively.
#6 Development of a Colic Scoring System to Predict Outcome in Horses – PubMed
https://pubmed.ncbi.nlm.nih.gov/34692803/
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. A retrospective, multi-institutional clinical study was performed to determine clinical parameters associated with survival of horses with colic, and to use them to develop a colic survival scoring system. The scoring system was then validated using clinical data in the prospective portion of the study. Medical records from 67 horses presenting for acute abdominal pain were evaluated to develop the colic assessment score. Twenty eight variables were compared between survivors and non-survivors and entered into logistic regression models for survival. Of these, six variables were included in the colic assessment score. A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%.
#7 Evaluation of Clinical and Laboratory Variables as Prognostic Indicators in Hospitalised Gastrointestinal Colic Horses
https://pmc.ncbi.nlm.nih.gov/articles/PMC1820986/
The outcome for all analyses was survival/non-survival. […] In conclusion, traditional variables as heart rate, mucous membranes and PCV were the important predictors for the outcome in hospitalised colic cases. […] The purpose of the present study was to evaluate clinical and laboratory variables as prognostic indicators in medically and surgically treated colic cases in a hospital situation. […] The final multiple logistic model included PCV as the only significant predictor in medically treated cases and heart rate and abnormal mucous membranes as significant predictors in surgically treated cases. […] In conclusion, traditional clinical variables as heart rate and presence of abnormal mucous membranes in surgical and PCV in medical colic cases were the significant predictors for the outcome.
#8 Evaluation of Clinical and Laboratory Variables as Prognostic Indicators in Hospitalised Gastrointestinal Colic Horses
https://pmc.ncbi.nlm.nih.gov/articles/PMC1820986/
The outcome for all analyses was survival/non-survival. […] In conclusion, traditional variables as heart rate, mucous membranes and PCV were the important predictors for the outcome in hospitalised colic cases. […] The purpose of the present study was to evaluate clinical and laboratory variables as prognostic indicators in medically and surgically treated colic cases in a hospital situation. […] The final multiple logistic model included PCV as the only significant predictor in medically treated cases and heart rate and abnormal mucous membranes as significant predictors in surgically treated cases. […] In conclusion, traditional clinical variables as heart rate and presence of abnormal mucous membranes in surgical and PCV in medical colic cases were the significant predictors for the outcome.
#9 Development of a Colic Scoring System to Predict Outcome in Horses – PubMed
https://pubmed.ncbi.nlm.nih.gov/34692803/
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. A retrospective, multi-institutional clinical study was performed to determine clinical parameters associated with survival of horses with colic, and to use them to develop a colic survival scoring system. The scoring system was then validated using clinical data in the prospective portion of the study. Medical records from 67 horses presenting for acute abdominal pain were evaluated to develop the colic assessment score. Twenty eight variables were compared between survivors and non-survivors and entered into logistic regression models for survival. Of these, six variables were included in the colic assessment score. A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%.
#10 Development of a Colic Scoring System to Predict Outcome in Horses. | Research Bank
https://madbarn.com/research/development-of-a-colic-scoring-system-to-predict-outcome-in-horses/?srsltid=AfmBOorunK0bHhJkiKVsZhkbUYqPmhjMohP0oslcd1NOhvvoeymegPzu
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. […] The scoring system was then validated using clinical data in the prospective portion of the study. […] A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%. […] Horses from the prospective portion of the study that received a score 7 were classified as predicted to die and those with a score 7 were predicted to survive. […] The classification was compared to the actual outcome, of which the sensitivity, specificity, positive and negative predictive values of the colic assessment score were 84, 62, 88, and 52%, respectively.
#11 Development of a Colic Scoring System to Predict Outcome in Horses – PubMed
https://pubmed.ncbi.nlm.nih.gov/34692803/
Horses from the prospective portion of the study that received a score 7 were classified as predicted to die and those with a score 7 were predicted to survive. The classification was compared to the actual outcome, of which the sensitivity, specificity, positive and negative predictive values of the colic assessment score were 84, 62, 88, and 52%, respectively.
#12 Development of a Colic Scoring System to Predict Outcome in Horses. | Research Bank
https://madbarn.com/research/development-of-a-colic-scoring-system-to-predict-outcome-in-horses/?srsltid=AfmBOorunK0bHhJkiKVsZhkbUYqPmhjMohP0oslcd1NOhvvoeymegPzu
Acute abdominal pain in the horse is a common emergency presenting to equine practices. The wide variety of etiologies makes prognosticating survival a challenge. […] The scoring system was then validated using clinical data in the prospective portion of the study. […] A total colic assessment score range was from 0 to 12, with the highest score representing the lowest probability of survival. The optimal cutoff value to predict survival was seven resulting in an 86% sensitivity and 64% specificity with a positive predictive value of 88% and a negative predictive value of 57%. […] Horses from the prospective portion of the study that received a score 7 were classified as predicted to die and those with a score 7 were predicted to survive. […] The classification was compared to the actual outcome, of which the sensitivity, specificity, positive and negative predictive values of the colic assessment score were 84, 62, 88, and 52%, respectively.
#13 Predicting the Outcome of Colic – The Horse
https://thehorse.com/15714/predicting-the-outcome-of-colic/
Colic is a common problem in horses. Establishing a plan for treatment and predicting the possible outcome of a case of colic is important to both the attending veterinarian and the anxious owner of the horse. […] A recent study has been conducted to assess the clinical utility of abdominal fluid analysis in predicting outcome (survival vs nonsurvival), lesion type (strangulating vs nonstrangulating), and whether medical or surgical treatment is indicated for horses with colic. […] Results indicate that abdominal fluid color and specific gravity had a high positive prediction value for lesion type, and that patient age and abdominal fluid color had a high positive prediction value for patient outcome. Horses with darker fluid were more likely to have a poorer long term outcome. An evaluation of abdominal fluid color and specific gravity could provide clinicians with useful information regarding patient outcome and lesion type. […] The researchers advise that abdominal fluid alone cannot be reliably used to predict treatment type, lesion type, or outcome but it can provide important clinically relevant information.
#14 Predicting the Outcome of Colic – The Horse
https://thehorse.com/15714/predicting-the-outcome-of-colic/
Colic is a common problem in horses. Establishing a plan for treatment and predicting the possible outcome of a case of colic is important to both the attending veterinarian and the anxious owner of the horse. […] A recent study has been conducted to assess the clinical utility of abdominal fluid analysis in predicting outcome (survival vs nonsurvival), lesion type (strangulating vs nonstrangulating), and whether medical or surgical treatment is indicated for horses with colic. […] Results indicate that abdominal fluid color and specific gravity had a high positive prediction value for lesion type, and that patient age and abdominal fluid color had a high positive prediction value for patient outcome. Horses with darker fluid were more likely to have a poorer long term outcome. An evaluation of abdominal fluid color and specific gravity could provide clinicians with useful information regarding patient outcome and lesion type. […] The researchers advise that abdominal fluid alone cannot be reliably used to predict treatment type, lesion type, or outcome but it can provide important clinically relevant information.
#15 From Prediction to Precision: Explainable AI-Driven Insights for Targeted Treatment in Equine Colic
https://www.mdpi.com/2076-2615/15/2/126
Colic is a critical health issue for horses, often requiring immediate and precise intervention to improve survival rates. […] This study integrates machine learning and explainable artificial intelligence (XAI) to predict survival outcomes in horses with colic, using clinical, procedural, and diagnostic data. […] The prognoses and outcomes of colic cases are highly variable, influenced by factors such as lesion type, age, and systemic health parameters. […] The success of colic management depends on several preoperative, intraoperative, and postoperative factors. […] Predictive models have emerged as a transformative tool in equine treatment and emergencies, particularly in managing complex and critical conditions like colic. […] The integration of explainable artificial intelligence (XAI) techniques, such as SHAP (Shapley additive explanations), transforms these âblack-boxâ models into interpretable frameworks.
#16 From Prediction to Precision: Explainable AI-Driven Insights for Targeted Treatment in Equine Colic
https://www.mdpi.com/2076-2615/15/2/126
Colic is a critical health issue for horses, often requiring immediate and precise intervention to improve survival rates. […] This study integrates machine learning and explainable artificial intelligence (XAI) to predict survival outcomes in horses with colic, using clinical, procedural, and diagnostic data. […] The prognoses and outcomes of colic cases are highly variable, influenced by factors such as lesion type, age, and systemic health parameters. […] The success of colic management depends on several preoperative, intraoperative, and postoperative factors. […] Predictive models have emerged as a transformative tool in equine treatment and emergencies, particularly in managing complex and critical conditions like colic. […] The integration of explainable artificial intelligence (XAI) techniques, such as SHAP (Shapley additive explanations), transforms these âblack-boxâ models into interpretable frameworks.
#17 From Prediction to Precision: Explainable AI-Driven Insights for Targeted Treatment in Equine Colic
https://www.mdpi.com/2076-2615/15/2/126
This study highlights the transformative potential of explainable artificial intelligence (XAI) in advancing equine colic management, with personalized insights derived through SHAP (Shapley additive explanations) emerging as the most impactful contribution. […] By combining global and local explanations, SHAP provides a robust framework for understanding survival determinants, enabling targeted and evidence-based interventions. […] Personalized insights derived through SHAP represent the most transformative finding of this study.
#18 Horse Colic | PDF
https://www.scribd.com/document/668561861/horse-colic
This document describes a machine learning project that aims to predict the survival probability of horses with colic by developing predictive models using historical medical records. […] The models evaluate various medical conditions and features to determine likelihood of survival. […] Accurately predicting colic occurrences could help veterinarians and owners make informed decisions to improve treatment and care. […] The project uses a dataset of 368 horse cases with 28 attributes related to symptoms, test results, and outcomes to build and validate classification models.
#19 Do Risk Factors During Infancy Predict Eosinophilic Esophagitis – Practical Gastro
https://practicalgastro.com/2019/01/19/do-risk-factors-during-infancy-predict-eosinophilic-esophagitis/
Infant colic is typically defined as excessive amounts of crying in the first 3 months of life. […] It is also unclear as to the long-term outcome of infants with colic. […] Long-term follow up demonstrated that there was no difference between groups in regards to internalizing behavioral problems as well as parental perceptions of crying, feeding, sleeping, and family function. […] This study appears to demonstrate that infant colic does not lead to long-term behavioral difficulties and suggests that probiotic use during infancy has no benefit in later childhood behavior.
#20 Do Risk Factors During Infancy Predict Eosinophilic Esophagitis – Practical Gastro
https://practicalgastro.com/2019/01/19/do-risk-factors-during-infancy-predict-eosinophilic-esophagitis/
Infant colic is typically defined as excessive amounts of crying in the first 3 months of life. […] It is also unclear as to the long-term outcome of infants with colic. […] Long-term follow up demonstrated that there was no difference between groups in regards to internalizing behavioral problems as well as parental perceptions of crying, feeding, sleeping, and family function. […] This study appears to demonstrate that infant colic does not lead to long-term behavioral difficulties and suggests that probiotic use during infancy has no benefit in later childhood behavior.
#21 Development of a Colic Scoring System to Predict Outcome in Horses. | Research Bank
https://madbarn.com/research/development-of-a-colic-scoring-system-to-predict-outcome-in-horses/?srsltid=AfmBOorunK0bHhJkiKVsZhkbUYqPmhjMohP0oslcd1NOhvvoeymegPzu
The development and validation of a colic scoring system can assist veterinary professionals in predicting survival outcomes in horses presenting with acute abdominal pain. […] Validation results demonstrate that this scoring system can indeed provide a reliable estimation of survival probability, supporting its potential application in equine practices.
#22 Horse Colic | PDF
https://www.scribd.com/document/668561861/horse-colic
This document describes a machine learning project that aims to predict the survival probability of horses with colic by developing predictive models using historical medical records. […] The models evaluate various medical conditions and features to determine likelihood of survival. […] Accurately predicting colic occurrences could help veterinarians and owners make informed decisions to improve treatment and care. […] The project uses a dataset of 368 horse cases with 28 attributes related to symptoms, test results, and outcomes to build and validate classification models.
#23 From Prediction to Precision: Explainable AI-Driven Insights for Targeted Treatment in Equine Colic
https://www.mdpi.com/2076-2615/15/2/126
This study highlights the transformative potential of explainable artificial intelligence (XAI) in advancing equine colic management, with personalized insights derived through SHAP (Shapley additive explanations) emerging as the most impactful contribution. […] By combining global and local explanations, SHAP provides a robust framework for understanding survival determinants, enabling targeted and evidence-based interventions. […] Personalized insights derived through SHAP represent the most transformative finding of this study.
#24 From Prediction to Precision: Explainable AI-Driven Insights for Targeted Treatment in Equine Colic
https://www.mdpi.com/2076-2615/15/2/126
This study highlights the transformative potential of explainable artificial intelligence (XAI) in advancing equine colic management, with personalized insights derived through SHAP (Shapley additive explanations) emerging as the most impactful contribution. […] By combining global and local explanations, SHAP provides a robust framework for understanding survival determinants, enabling targeted and evidence-based interventions. […] Personalized insights derived through SHAP represent the most transformative finding of this study.