MyMedR

Displaying all 3 publications

Abstract:

Sort:

Fulltext Assessment of predictive models for chlorophyll-a concentration of a tropical lake

Malek S, Syed Ahmad SM, Singh SK, Milow P, Salleh A

BMC Bioinformatics, 2011;12 Suppl 13:S12.
PMID: 22372859 DOI: 10.1186/1471-2105-12-S13-S12

This study assesses four predictive ecological models; Fuzzy Logic (FL), Recurrent Artificial Neural Network (RANN), Hybrid Evolutionary Algorithm (HEA) and multiple linear regressions (MLR) to forecast chlorophyll- a concentration using limnological data from 2001 through 2004 of unstratified shallow, oligotrophic to mesotrophic tropical Putrajaya Lake (Malaysia). Performances of the models are assessed using Root Mean Square Error (RMSE), correlation coefficient (r), and Area under the Receiving Operating Characteristic (ROC) curve (AUC). Chlorophyll-a have been used to estimate algal biomass in aquatic ecosystem as it is common in most algae. Algal biomass indicates of the trophic status of a water body. Chlorophyll- a therefore, is an effective indicator for monitoring eutrophication which is a common problem of lakes and reservoirs all over the world. Assessments of these predictive models are necessary towards developing a reliable algorithm to estimate chlorophyll- a concentration for eutrophication management of tropical lakes.
Wavelet Analysis of Resultant Velocity Belonging to Genuine and Forged Signatures

Syed Ahmad SM, Loo LY, Wan Adnan WA, Md Anwar R

J Forensic Sci, 2017 Mar;62(2):374-381.
PMID: 28000207 DOI: 10.1111/1556-4029.13303

This study presents a wavelet analysis of resultant velocity features belonging to genuine and forged groups of signature sample. Signatures of individuals were initially classified based on visual human perceptions of their relative sizes, complexities, and legibilities of the genuine counterparts. Then, the resultant velocity was extracted and modeled through wavelet analysis from each sample. The wavelet signal was decomposed into several layers based on maximum overlap discrete wavelet transform (MODWT). Next, the zero crossing rate features were calculated from all the high wavelet sub-bands. A total of seven hypotheses were then tested using a two-way ANOVA testing methodology. Of these, four hypotheses were conducted to test for significance differences between distributions. In addition, three hypotheses were run to provide test for interaction between two factors of signature authentication versus perceived classification. The results demonstrated that both feature distributions belonging to genuine and forged groups of samples cannot be distinguished by themselves. Instead, they were significantly different under the influence of two other inherent factors, namely perceived size and legibility. Such new findings are useful information particularly in providing bases for forensic justifications in establishing the authenticity of handwritten signature specimens.
Machine learning-based risk prediction model for medication administration errors in neonatal intensive care units: A prospective direct observational study

Henry Basil J, Lim WH, Syed Ahmad SM, Menon Premakumar C, Mohd Tahir NA, Mhd Ali A, et al.

Digit Health, 2024;10:20552076241286434.
PMID: 39430694 DOI: 10.1177/20552076241286434

OBJECTIVE: Neonates' physiological immaturity and complex dosing requirements heighten their susceptibility to medication administration errors (MAEs), with the potential for severe harm and substantial economic impact on healthcare systems. Developing an effective risk prediction model for MAEs is crucial to reduce and prevent harm.
METHODS: This national-level, multicentre, prospective direct observational study was conducted in neonatal intensive care units (NICUs) of five public hospitals in Malaysia. Randomly selected nurses were directly observed during medication preparation and administration. Each observation was independently assessed for errors. Ten machine learning (ML) algorithms were applied with features derived from systematic reviews, incident reports, and expert consensus. Model performance, prioritising F1-score for MAEs, was evaluated using various measures. Feature importance was determined using the permutation-feature importance for robust comparison across ML algorithms.
RESULTS: A total of 1093 doses were administered to 170 neonates, with mean age and birth weight of 33.43 (SD ± 5.13) weeks and 1.94 (SD ± 0.95) kg, respectively. F1-scores for the ten models ranged from 76.15% to 83.28%. Adaptive boosting (AdaBoost) emerged as the best-performing model (F1-score: 83.28%, accuracy: 77.63%, area under the receiver operating characteristic: 82.95%, precision: 84.72%, sensitivity: 81.88% and negative predictive value: 64.00%). The most influential features in AdaBoost were the intravenous route of administration, working hours, and nursing experience.
CONCLUSIONS: This study developed and validated an ML-based model to predict the presence of MAEs among neonates in NICUs. AdaBoost was identified as the best-performing algorithm. Utilising the model's predictions, healthcare providers can potentially reduce MAE occurrence through timely interventions.

Filters

Please provide feedback to Administrator ([email protected])

External Links