Search

Clinical information on molecular subtypes and the Ki67 index is critical for breast cancer (BC) prognosis and personalised treatment plan. Extracting such information into structured data is essential for research, auditing, and cancer incidence reporting and underpins the potential for automated decision support. Herewith, we developed a rule-based natural language processing algorithm that retrieved and extracted important BC parameters from free-text pathology reports towards exploring molecular subtypes and Ki67-proliferation trends. We considered malignant BC pathology reports with different free-text narrative attributes from the South African National Health Laboratory Service. The reports were preprocessed and parsed through the algorithm. Parameters extracted by the algorithm were validated against manually extracted parameters. For all parameters extracted, we obtained accurate annotations of 83-100%, 93-100%, 91-100%, and 92-100% precision, recall, F 1 -score, and kappa, respectively. There was a significant trend in the proportion of each molecular subtype by patient age, histologic type, grade, Ki67, and race. The findings also showed significant association in the Ki67 trend with hormone receptors, human epidermal growth factors, age, grade, and race. Our approach bridges the gap between data availability and actionable knowledge and provides a framework that could be adapted and reused in other cancers and beyond cancer studies. Information extracted from these reports showed interesting trends that may be exploited for BC screening and treatment resources in South Africa. Finally, this study strongly encourages the implementation of a synoptic style pathology report in South Africa. [ABSTRACT FROM AUTHOR]

The aim of this pilot study was to develop logistic regression (LR) and support vector machine (SVM) models that differentiate low from high risk for prolonged hospital length of stay (LOS) in a South African cohort of 383 colorectal cancer patients who underwent surgical resection with curative intent. Additionally, the impact of 10-fold cross-validation (CV), Monte Carlo CV, and bootstrap internal validation methods on the performance of the two models was evaluated. The median LOS was 9 days, and prolonged LOS was defined as greater than 9 days post-operation. Preoperative factors associated with prolonged LOS were a prior history of hypertension and an Eastern Cooperative Oncology Group score between 2 and 4. Postoperative factors related to prolonged LOS were the need for a stoma as part of the surgical procedure and the development of post-surgical complications. The risk of prolonged LOS was higher in male patients and in any patient with lower preoperative hemoglobin. The highest area under the receiving operating characteristics (AU-ROC) was achieved using LR of 0.823 (CI = 0.798–0.849) and SVM of 0.821 (CI = 0.776–0.825), with each model using the Monte Carlo CV method for internal validation. However, bootstrapping resulted in models with slightly lower variability. We found no significant difference between the models across the three internal validation methods. The LR and SVM algorithms used in this study required incorporating important features for optimal hospital LOS predictions. The factors identified in this study, especially postoperative complications, can be employed as a simple and quick test clinicians may flag a patient at risk of prolonged LOS. [ABSTRACT FROM AUTHOR]

The inconsistency in the eating quality characteristics of meats, predominantly tenderness, is probably the most critical problem faced by the meat industry worldwide. Consumers consider tenderness to be the single most important component of meat quality. An alternative method for increasing meat tenderness may exist in the form of electrical stimulation of the carcass shortly following slaughter. The aim of this research was to study the effect of electrical stimulation on the consumer acceptance of, preference for and consumption intent regarding mutton of the recently introduced class-AB sheep carcasses (carcasses from sheep with one to two permanent incisors) in South Africa. A total of 22 wethers of class-AB, weighing between 45 and 50 kg, was selected from a homogeneous group of Dorpers. Carcasses were divided into two groups, one was electrically stimulated (0.4 amp/h for 45 sec) and the other group not stimulated. Samples of the left M. longissimus thoracis et lumborum of both groups were oven roasted and a consumer panel evaluated the acceptability of the mutton regarding certain sensory characteristics. Three consumer sensory tests, namely the hedonic rating of the acceptability of each sensory attribute, a preference test and a food action rating test, were conducted in sequence. The acceptability of the juiciness, tenderness, flavour and overall acceptability were not significantly influenced by the electrical stimulation of carcasses. Samples from both the electrically stimulated and non-stimulated carcasses were highly acceptable to consumers. No significant differences in preference or percentage cooking losses were obtained. The present results indicate that electrical stimulation of class-AB carcasses did not have a significant influence on the consumer's acceptance of, nor consumption intent towards the class-AB mutton. This study shows that consumers revealed a positive attitude by declaring their intention to eat samples from both... [ABSTRACT FROM AUTHOR]

Eighty-nine intact male, castrates and female South African indigenous goats in three age groups (0, 2 - 6 and 8 permanent incisors) and two pre-slaughter conditioning groups; namely, the non-conditioned which were slaughtered within three months of purchase and the pre-slaughter conditioned, which were slaughtered 6 - 10 months after purchase or birth were used. The effect of sex, age and pre-slaughter conditioning on live animal, carcass dimensions and carcass composition were evaluated. The goats were large with live weight, carcass weight and carcass dimensions in the range of the large breeds of southern Africa. They had a high lean and low fat content. Intact males were suited for high chevon yield because they were heavy, had a high lean and low fat content, and losses during dressing and chilling were reduced by improved nutrition. Goats between 2 - 6 teeth yielded heavy carcasses that were comparable to goats in the 8-teeth group, and had proportionately more lean and less carcass fat. The hind limb was ideal for high lean and low fat, high value cuts but the dorsal trunk was bony and yielded less lean. Pre-slaughter conditioning improved the overall size of the goats and reduced the losses during slaughter and chilling. It also improved the lean!bone and lean and fat/bone indices. [ABSTRACT FROM AUTHOR]

Consumer sensory evaluations of oven-roasted goat and sheep m. longissimus dorsi samples were conducted in two series to determine the acceptability of chevon from indigenous South African goats to consumers. Chevon samples were from goat carcasses of known description. In series I, castrate and female goats and female sheep, all with 2 - 6 permanent incisors, were compared. Castrate males were significantly heavier and yielded heavier carcasses than the female goats. Nonetheless, the two groups did not differ significantly in carcass and meat characteristics. Cooking losses from mutton samples were significantly higher than losses from chevon from female goats only. In series II, male kids (milk teethed), old does (8 permanent teeth) and sheep (2 - 6 permanent teeth) were compared. Does were heavier at slaughter, but the mean carcass weight did not differ significantly from that of the kids. There were no significant differences between the does and kids in carcass tissue composition and sarcomere lengths. The pHu of does was significantly higher than that of kids. Cooking losses from mutton and chevon samples in series II did not differ significantly. Amongst the consumer characteristics, level of education was the most important determinant of consumer acceptance of the sensory attributes and intended frequency of consumption in both series. Population group was a significant factor in the judgement of the more diverse meats of series II only. Sensory evaluations indicate that all meat types were highly acceptable to the consumers who on average were willing to eat any of the meats at least once a week. The study indicated that chevon from indigenous South African goats is acceptable to consumers and may be as acceptable as mutton, provided that the meat is from goats of about two years of age or younger. [ABSTRACT FROM AUTHOR]

Background: South Africa (SA) has the highest incidence of colorectal cancer (CRC) in Sub-Saharan Africa (SSA). However, there is limited research on CRC recurrence and survival in SA. CRC recurrence and overall survival are highly variable across studies. Accurate prediction of patients at risk can enhance clinical expectations and decisions within the South African CRC patients population. We explored the feasibility of integrating statistical and machine learning (ML) algorithms to achieve higher predictive performance and interpretability in findings. Methods: We selected and compared six algorithms:- logistic regression (LR), naïve Bayes (NB), C5.0, random forest (RF), support vector machine (SVM) and artificial neural network (ANN). Commonly selected features based on OneR and information gain, within 10-fold cross-validation, were used for model development. The validity and stability of the predictive models were further assessed using simulated datasets. Results: The six algorithms achieved high discriminative accuracies (AUC-ROC). ANN achieved the highest AUC-ROC for recurrence (87.0%) and survival (82.0%), and other models showed comparable performance with ANN. We observed no statistical difference in the performance of the models. Features including radiological stage and patient's age, histology, and race are risk factors of CRC recurrence and patient survival, respectively. Conclusions: Based on other studies and what is known in the field, we have affirmed important predictive factors for recurrence and survival using rigorous procedures. Outcomes of this study can be generalised to CRC patient population elsewhere in SA and other SSA countries with similar patient profiles., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Achilonu, Fabian, Bebington, Singh, Eijkemans and Musenge.)