Posttransfusion Purpura: A Rare Entity

Abstract

Post-transfusion purpura (PTP) is a rare disease characterized by life-threatening thrombocytopenia after transfusion of any platelet-containing blood products, such as platelets(PLT) or packed red blood cells (PRBCs). We report an interesting case of PTP in a young lady after receiving multiple blood products. CASE PRESENTATION:A 36-year-old female with a past medical history of diabetes mellitus and left-sided below-knee amputation (BKA) was admitted to the Intensive Care Unit (ICU) for emphysematous osteomyelitis with intraosseous gas in the calcaneus, cuboid, and fifth metatarsal base of the right lower extremity. She underwent right-sided BKA, requiring multiple PRBC transfusions due to a combination of blood loss during surgery and chronic anemia. The initial platelet count was normal at 329,000/uL. Five days after the PRBC transfusion, it trended down to 17,000/uL and there was concurrent development of a purpuric rash over both arms. Bloodwork was notable for elevated prothrombin time and activated partial thromboplastin time. Hemolysis workup and Coombs test were negative. Fibrinogen was elevated, ruling out disseminated intravascular coagulation. PTP was suspected based on the clinical presentation and exclusion of other etiologies. Anti-human platelet antigen-1a (HPA-1a) antibodies were obtained. Empiric treatment with intravenous immunoglobulin (IVIG) and steroids was promptly initiated. Platelet count improved to 157,000/uL after four doses of IVIG. The patient tested positive for HPA-1a. However, due to the urgent need for treatment, the test sample for the anti-platelet antibodies was drawn after the initiation of IVIG. The development of thrombocytopenia in the classic time frame with the characteristic rash and improvement after receiving IVIG make PTP the most likely diagnosis. She was recommended to receive only washed PRBCs in the future to prevent a recurrence. DISCUSSION: PTP is a rare, underdiagnosed, and potentially fatal reaction, with the development of severe thrombocytopenia 2-14 days after transfusion of platelet-containing blood products. It is considered to be caused by alloimmunization against platelet antigens, with HPA-1a being the most common antibody1. Some cases of HPA-1b mediated PTP have been reported as well2. Diagnosis is often subtle and challenging, therefore a strong clinical suspicion is needed. A history of blood product transfusion a few days before the development of thrombocytopenia should make the physician think about the possibility of PTP. Treatment includes IVIG, steroids, or plasmapheresis3, and initiation of treatment should not wait for diagnostic confirmation.CONCLUSIONS: Clinicians should have high clinical suspicion for PTP in patients with acute, severe thrombocytopenia which develops after blood transfusions, and treatment should be initiated early to favorably alter the course of the disease.

Recognition of Emotion with Intensity from Speech Signal Using 3D Transformed Feature and Deep Learning

“…As REIS uses 3D transformed features, the 3D CNN is the most suitable for feature extraction. On the other hand, Bi-LSTM is considered due to its capability to handle sequential data and its performance in recent studies [34,35]. Figure 5a shows the basic structure of the proposed DL architecture having four 3D CNN feature blocks (FB) and Bi-LSTM with a TDF layer.…”

“…The training set, including 1350 (=150 × 9) samples, was used to train the model, and the test set with the remaining 342 (=38 × 9) samples was reserved to evaluate the generalization ability of the model after training. Notably, the RAVDESS dataset is used in several studies, including several recent ones [8,39,40]. However, all the existing studies consider emotion classification only, without considering the emotional intensity issue.…”

Advanced Fusion-Based Speech Emotion Recognition System Using a Dual-Attention Mechanism with Conv-Caps and Bi-GRU Features

“…Then, in [41], the authors utilized a CNN model to learn the salient emotional features. Later, in [42], the authors implemented a CNN model to obtain emotional information from spectrograms to identify the speech emotion [43]. A spectrogram is a two-dimensional visualization of a speech signal, is used in 2D-CNN models to extract high-level discriminative features, and has become more prevalent in this era [44].…”

“…A spectrogram is a two-dimensional visualization of a speech signal, is used in 2D-CNN models to extract high-level discriminative features, and has become more prevalent in this era [44]. Zhao et al [45] extracted features using different spectrogram dimensions using CNNs and passed them through to an LSTM network. The LSTM network was used to learn global contextual information from the resulting features of the CNN.…”

“…Speech-based emotion recognition tasks are receiving increasing attention in many areas, such as forensic sciences [4], customer support call review and analysis [5], mental health surveillance, intelligent systems, and quality assessments of education [6]. Deep learning technology has accelerated the recognition of emotions from speech, but the research on SER still has deficiencies, such as shortages of training data and inadequate model performance [7,8]. However, emotion classification from speech in real-time is difficult due to several dependencies, such as speakers, cultures, genders, ages, and dialects [9].…”