Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 2 de 2
Filter
Add more filters










Database
Language
Publication year range
1.
Sensors (Basel) ; 23(5)2023 Mar 01.
Article in English | MEDLINE | ID: mdl-36904915

ABSTRACT

Topic modeling is a machine learning algorithm based on statistics that follows unsupervised machine learning techniques for mapping a high-dimensional corpus to a low-dimensional topical subspace, but it could be better. A topic model's topic is expected to be interpretable as a concept, i.e., correspond to human understanding of a topic occurring in texts. While discovering corpus themes, inference constantly uses vocabulary that impacts topic quality due to its size. Inflectional forms are in the corpus. Since words frequently appear in the same sentence and are likely to have a latent topic, practically all topic models rely on co-occurrence signals between various terms in the corpus. The topics get weaker because of the abundance of distinct tokens in languages with extensive inflectional morphology. Lemmatization is often used to preempt this problem. Gujarati is one of the morphologically rich languages, as a word may have several inflectional forms. This paper proposes a deterministic finite automaton (DFA) based lemmatization technique for the Gujarati language to transform lemmas into their root words. The set of topics is then inferred from this lemmatized corpus of Gujarati text. We employ statistical divergence measurements to identify semantically less coherent (overly general) topics. The result shows that the lemmatized Gujarati corpus learns more interpretable and meaningful subjects than unlemmatized text. Finally, results show that lemmatization curtails the size of vocabulary decreases by 16% and the semantic coherence for all three measurements-Log Conditional Probability, Pointwise Mutual Information, and Normalized Pointwise Mutual Information-from -9.39 to -7.49, -6.79 to -5.18, and -0.23 to -0.17, respectively.

2.
J Emerg Med ; 61(3): 241-251, 2021 09.
Article in English | MEDLINE | ID: mdl-34215470

ABSTRACT

BACKGROUND: There is no prior study that has documented emergency department (ED) outcomes or stratified mortality risks of cancer patients presenting with an acute venous thromboembolism (VTE). OBJECTIVE: To evaluate ED treatment of these patients, to document their outcomes, and to identify risk factors associated with death. METHODS: A retrospective cohort study was performed on active cancer patients presenting with deep venous thrombosis or pulmonary embolism to two academic EDs between July 2012 and June 2016. Key outcomes included mortality, ED revisit, and admission within 30 days. The patient cohort was characterized; crosstabs and regression analysis were performed to assess relative risks (RRs) and mitigating factors associated with 30-day mortality. RESULTS: Of 355 patients, 9% died and 38% had one or more ED revisits or admissions. Recent immobility (RR 2.341, 95% CI 1.227-4.465), poor functional status (RR 2.090, 95% CI 1.028-4.248), recent admission (RR 2.441, 95% CI 1.276-4.669), and metastatic cancer (RR 4.669, 95% CI 1.456-14.979) were major risk factors for mortality. ED-provided anticoagulation reduced the overall mortality risk (RR 0.274, 95% CI 0.146-0.515) and mitigated the risk from recent immobility (RR 1.250, 95% CI 0.462-3.381), especially among patients with good or fair functional status. CONCLUSION: Immobility and cancer morbidity are key risk factors for mortality after an acute VTE, but ED-provided anticoagulation mitigates the risk of immobility among healthier patients. Eastern Cooperative Oncology Group performance status can help clinicians risk stratify these patients at presentation.


Subject(s)
Neoplasms , Pulmonary Embolism , Venous Thromboembolism , Venous Thrombosis , Anticoagulants/therapeutic use , Emergency Service, Hospital , Humans , Neoplasms/complications , Retrospective Studies , Risk Factors
SELECTION OF CITATIONS
SEARCH DETAIL
...