LITERATURE UPDATE
neighbour, support vector machine, and Naive Bayes). The training set and test set were divided at a ratio of 7:3. The authors evaluated the performance of machine learning models on the test set using various metrics to select the most valuable model. The PLT-F method exhibited a high
degree of correlation with the PLT-I method (r=0.998). The random forest model emerged as the most valuable, boasting an accuracy of 0.893, an area under the curve of 0.954, an F1 score of 0.771, a recall of 0.719, a precision of 0.831, and a specificity of 0.950. The most important variable in the random forest model was mean cell volume, weighted at 15.09%.
In conclusion, the random forest model, which demonstrated high efficiency in this study, can be used to establish PLT reflex test rules based on the PLT-F method for the Sysmex XN- series automated haematology analyser.
Small bruise-like markings (petechiae) may be seen in cases of immune thrombocytopenic purpura.
crucial in the patient management of ulcerative colitis (UC); yet the significance of platelet-to-lymphocyte percentage ratio (PLpR) remains unknown, which was investigated in this study. The authors used data from three
clinical trials: ACT 1, PURSUIT, and UNIFI. In total, 7614 endoscopic procedures and 1365 patients were included for assessing severity and predicting outcome, respectively. The primary outcome was endoscopic remission, defined as a Mayo endoscopic score of 0. The diagnostic capacity of PLpR was evaluated by the area under the receiver operating characteristic curve (AUC) while multivariable logistic regression was employed to assess the prognostic power of PLpR.
PLpR showed higher AUCs than
C-reactive protein in identifying endoscopic remission (P<0.001) and improvement (P<0.001). Besides, combining PLpR with faecal calprotectin enhanced the power to distinguish disease activity. In therapeutic outcome analyses, higher PLpR level indicated worse long-term outcomes. PLpR ≥ 1016.7 predicted a lower likelihood of endoscopic remission (OR: 0.50 [95% CI: 0.39–0.65]; P<0.001), endoscopic improvement (OR: 0.45 [95% CI: 0.36–0.57]; P<0.001), clinical remission (OR: 0.50 [95% CI: 0.39–0.62]; P<0.001), histologic improvement (OR: 0.50 [95% CI: 0.31–0.79]; P=0.004), and histologic- endoscopic mucosal improvement (OR: 0.42 [95% CI: 0.27–0.66]; P<0.001).
58
Moreover, PLpR added the prognostic value to C-reactive protein, faecal calprotectin, clinical and endoscopic scores to predict long-term outcomes. In conclusion, PLpR could be a
promising biomarker for monitoring disease activity and predicting long-term therapeutic outcomes in UC.
Establishing reflex test rules for platelet fluorescent counting method using machine learning models on Sysmex XN-series hematology analyzer.
Zhou Z, Guo M, Wu K, Yue Z. Int J Lab Hematol. 2024 Dec; 46 (6): 1036–43. doi: 10.1111/ijlh.14353.
The platelet fluorescent counting (PLT-F) method is utilied as a reflex test method following the initial test of the platelet impedance counting (PLT-I) method in clinical practice on the Sysmex XN-series automated haematology analyser. The aim in this study is to establish reflex test rules for the PLT-F method by combining multiple parameters provided by the “CBC + DIFF” mode of the Sysmex XN-series automated haematology analyser. The authors tested 120 samples to evaluate the baseline bias between the PLT-F and PLT-I methods. Then, they selected 1256 samples to establish and test reflex test rules using seven machine learning models (decision Tree, random forest, neural network, logistic regression, k-nearest
Platelet Count During Course of Cardiogenic Shock. Schupp T, Rusnak J, Forner J et al. ASAIO J. 2024 Jan 1; 70 (1): 44–52. doi: 10.1097/MAT.0000000000002066.
This study investigates the prognostic value of the platelet count in patients with cardiogenic shock (CS). Limited data regarding the prognostic value of platelets in patients suffering from CS are available.
Consecutive patients with CS from 2019 to 2021 were included at one institution. Firstly, the prognostic value of the baseline platelet count was tested for 30-day all-cause mortality. Thereafter, the prognostic impact of platelet decline during course of intensive care unit (ICU) hospitalisation was assessed. A total of 249 CS patients
were included with a median platelet count of 224 × 106
/mL. No
association of the baseline platelet count with the risk of 30-day all- cause mortality was found (log-rank P=0.563; hazard ratio [HR] = 0.879; 95% confidence interval [CI] 0.557–1.387; P=0.579). In contrast, a decrease of platelet count by ≥25% from day 1 to day 3 was associated with an increased risk of 30-day all-cause mortality (55% vs. 39%; log-rank P=0.045; HR = 1.585; 95% CI 0.996–2.521; P=0.052), which was still evident after multivariable adjustment (HR = 1.951; 95% CI 1.116–3.412; P=0.019).
Platelet decrease during the course of ICU hospitalisation but not the baseline platelet count was associated with an increased risk of 30-day all-cause mortality in CS patients.
FEBRUARY 2025
WWW.PATHOLOGYINPRACTICE.COM
User:Hektor CC BY-SA 3.0 Wikimedia Commons
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60