Machine learning-derived electrocardiographic algorithm for the detection of cardiac amyloidosis.

BACKGROUND: Diagnosis of cardiac amyloidosis (CA) requires advanced imaging techniques. Typical surface ECG patterns have been described, but their diagnostic abilities are limited. OBJECTIVE: The aim was to perform a thorough electrophysiological characterisation of patients with CA and derive an easy-to-use tool for diagnosis. METHODS: We applied electrocardiographic imaging (ECGI) to acquire electroanatomical maps in patients with CA and controls. A machine learning approach was then used to decipher the complex data sets obtained and generate a surface ECG-based diagnostic tool. FINDINGS: Areas of low voltage were localised in the basal inferior regions of both ventricles and the remaining right ventricular segments in CA. The earliest epicardial breakthrough of myocardial activation was visualised on the right ventricle. Potential maps revealed an accelerated and diffuse propagation pattern. We correlated the results from ECGI with 12-lead ECG recordings. Ventricular activation correlated best with R-peak timing in leads V1-V3. Epicardial voltage showed a strong positive correlation with R-peak amplitude in the inferior leads II, III and aVF. Respective surface ECG leads showed two characteristic patterns. Ten blinded cardiologists were asked to identify patients with CA by analysing 12-lead ECGs before and after training on the defined ECG patterns. Training led to significant improvements in the detection rate of CA, with an area under the curve of 0.69 before and 0.97 after training. INTERPRETATION: Using a machine learning approach, an ECG-based tool was developed from detailed electroanatomical mapping of patients with CA. The ECG algorithm is simple and has proven helpful to suspect CA without the aid of advanced imaging modalities.

Ca2+ imaging of neurons in freely moving rats with automatic post hoc histological identification.

BACKGROUND: Cognitive neuroscientists aim to understand behavior often based on the underlying activity of individual neurons. Recently developed miniaturized epifluorescence microscopes allow recording of cellular calcium transients, resembling neuronal activity, of individual neurons even in deep brain areas in freely behaving animals. At the same time, molecular markers allow the characterization of diverse neuronal subtypes by post hoc immunohistochemical labeling. Combining both methods would allow researchers to increase insights into how individual neuronal activity and entities contribute to behavior. NEW METHOD: Here, we present a novel method for identifying the same neurons, recorded with calcium imaging using a miniaturized epifluorescence microscope, post hoc in fixed histological sections. This allows immunohistochemical investigations to detect the molecular signature of in vivo recorded neurons. Our method utilizes the structure of blood vessels for aligning in vivo acquired 2D images with a reconstructed 3D histological model. RESULTS: We automatically matched, 60 % of all in vivo recorded cells post hoc in histology. Across all animals, we successfully matched 43 % to 89 % of the recorded neurons. We provide a measure for the confidence of matched cells and validated our method by multiple simulation studies. COMPARISON WITH EXISTING METHODS: To our knowledge, we present the first method for matching cells, recorded with a miniaturized epifluorescence microscope in freely moving animals, post hoc in histological sections. CONCLUSIONS: Our method allows a comprehensive analysis of how cortical circuits relate to freely moving animal behavior by combining functional activity of individual neurons with their underlying histological profiles.

Activity of Prefrontal Neurons Predict Future Choices during Gambling.

Neuronal signals in the prefrontal cortex have been reported to predict upcoming decisions. Such activity patterns are often coupled to perceptual cues indicating correct choices or values of different options. How does the prefrontal cortex signal future decisions when no cues are present but when decisions are made based on internal valuations of past experiences with stochastic outcomes? We trained rats to perform a two-arm bandit-task, successfully adjusting choices between certain-small or possible-big rewards with changing long-term advantages. We discovered specialized prefrontal neurons, whose firing during the encounter of no-reward predicted the subsequent choice of animals, even for unlikely or uncertain decisions and several seconds before choice execution. Optogenetic silencing of the prelimbic cortex exclusively timed to encounters of no reward, provoked animals to excessive gambling for large rewards. Firing of prefrontal neurons during outcome evaluation signals subsequent choices during gambling and is essential for dynamically adjusting decisions based on internal valuations.

Machine learning for fast identification of bacteraemia in SIRS patients treated on standard care wards: a cohort study.

Bacteraemia is a life-threating condition requiring immediate diagnostic and therapeutic actions. Blood culture (BC) analyses often result in a low true positive result rate, indicating its improper usage. A predictive model might assist clinicians in deciding for whom to conduct or to avoid BC analysis in patients having a relevant bacteraemia risk. Predictive models were established by using linear and non-linear machine learning methods. To obtain proper data, a unique data set was collected prior to model estimation in a prospective cohort study, screening 3,370 standard care patients with suspected bacteraemia. Data from 466 patients fulfilling two or more systemic inflammatory response syndrome criteria (bacteraemia rate: 28.8%) were finally used. A 29 parameter panel of clinical data, cytokine expression levels and standard laboratory markers was used for model training. Model tuning was performed in a ten-fold cross validation and tuned models were validated in a test set (80:20 random split). The random forest strategy presented the best result in the test set validation (ROC-AUC: 0.729, 95%CI: 0.679-0.779). However, procalcitonin (PCT), as the best individual variable, yielded a similar ROC-AUC (0.729, 95%CI: 0.679-0.779). Thus, machine learning methods failed to improve the moderate diagnostic accuracy of PCT.

[18F]FDG-PET/CT and MRI for initial pelvic lymph node staging in patients with cervical carcinoma: The potential usefulness of [18F]FDG-PET/MRI.

The current study aimed to determine the optimum diagnostic imaging technique out of magnetic resonance imaging (MRI), 18F-fludeoxyglucose positron emission tomography/computed tomography ([18F]FDG-PET/CT, otherwise known as PET/CT) and [18F]FDG-PET/MRI (otherwise known as PET/MRI) for the pelvic lymph node staging (N-staging) of untreated cervical carcinoma (CC). A total of 27 patients were included in the present study. All patients had undergone pre-treatment with PET/CT and MRI ≤45 days prior to undergoing a lymphadenectomy. The results from PET (separated from PET/CT), MRI and the statistically combined results of (virtual) PET/MRI were compared to those from histological analyses (the gold standard). A per-patient-based analysis of the detection of pelvic lymph node metastases indicated that PET/MRI had a sensitivity of 64%. The specificity of PET/CT and MRI were 69 and 62%, respectively. The positive predictive value (PPV) was 69 and 64% for PET/CT and MRI, respectively. The negative predictive value (NPV) was 64 and 62% for PET/CT and MRI, respectively. The sensitivity of the PET-guided PET/MRI and the MRI-guided PET/MRI was 64% for both. The specificity of the PET-guided PET/MRI and the MRI-guided PET/MRI was 77 and 62%, respectively. The PPV was 75% for PET-guided PET/MRI and 64% for MRI-guided PET/MRI, and the NPV was 67 and 62%, respectively. PET/CT and the virtual PET/MRI exhibited the same low sensitivity (64%). PET/MRI exhibited slightly better results than PET/CT regarding specificity (77 vs. 69%, respectively), PPV (75 vs. 69%, respectively) and NPV (67 vs. 64%, respectively). The results of the present study suggested that PET/CT and MRI are not optimal diagnostic modalities, and that PET/MRI does not necessarily lead to better results than PET/CT, in the pelvic N-staging of CC.

Detection of Bone Metastases Using 11C-Acetate PET in Patients with Prostate Cancer with Biochemical Recurrence.

AIM: To evaluate the diagnostic accuracy of (11)C-acetate positron-emission tomography (PET) in the detection of bone metastasis in patients with prostate cancer with biochemical recurrence. PATIENTS AND METHODS: Ninety patients (100%) with rising prostate-specific antigen (PSA) levels (>0.2 ng/ml) after radical prostatectomy, who had both (11)C-acetate PET and bone scan performed and who had clinical follow-up/imaging follow-up for bone metastasis, considered a gold standard, were included. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for (11)C-acetate PET were calculated on a per-patient basis. RESULTS: (11)C-Acetate PET and (99m)Tc-dicarboxypropane-diphosphonate findings were concordant in 84 (93.3%) patients [35 (38.9%) true-positive, 49 (54.4%) true-negative]. Discordant findings were observed in six patients (6.7%). (11)C-Acetate PET presented two (2.2%) false-positive and four (4.4%) false-negative findings. The sensitivity, specificity, PPV, and NPV for (11)C-acetate PET were 89.7%, 96.1%, 94.6%, and 92.2%, respectively. The median PSA of patients with multiple skeletal metastases (median=23.64 ng/ml, range=3.16-551.1 ng/ml) differed significantly (p=0.018) from that of patients with focal metastases (median=6.7 ng/ml, range=0.31-12.8 ng/ml). CONCLUSION: (11)C-Acetate PET is a useful tool for patients with prostate cancer with biochemical recurrence, as it can depict multiple sites of recurrence and in particularly shows a high diagnostic value equivalent to that of bone scan for the detection of bone metastases.

Relevance of calcitonin cut-off in the follow-up of medullary thyroid carcinoma for conventional imaging and 18-fluorine-fluorodihydroxyphenylalanine PET.

AIM: The American thyroid association (ATA) recommends that additional imaging procedures supplement cervical ultrasonography (US) in any patient with a basal calcitonin value above 150 pg/ml in the follow-up of medullary thyroid carcinoma (MTC). The aim of the present study was to reaffirm or challenge this cut-off for 18-Fluorine-Fluorodihydroxyphenylalanine positron emission tomography (18F-DOPA PET) and conventional imaging ultrasonography (US), computed tomography (CT), magnetic resonance imaging (MRI)). MATERIALS AND METHODS: Thirty-nine patients (18 females, 21 males), mean age 62 years, range from 35 to 86, followed-up for MTC were included in the present retrospective study. In our patients 64 18F-DOPA scans, 28 neck US, 28 CT and 8 MRI were performed. For all cases basal calcitonin values were available. Sensitivity and specificity of 18F-DOPA PET and conventional imaging (US, CT, MRI) related to calcitonin values were calculated. RESULTS: According to the calcitonin cut-off of 150 pg/ml, we found the following sensitivities and specificities: 79% and 80% for 18F-DOPA PET, 75% and 92% for US, 80% and 25% for CT, 50% and 75% for MRI. Taking the level of detectable calcitonin, we calculated the following sensitivities: 52% for 18F-DOPA PET, 46% for US, 79% for CT and 38% for MRI. CONCLUSION: We cannot confirm the calcitonin cut-off proposed by the ATA for the detection of MTC recurrences and contemporaneously we cannot state that 18F-DOPA PET has a very high sensitivity. For the neck region 18F-DOPA PET and US showed similar results. 18F-DOPA PET/CT seems to be the best imaging modality for whole-body tumor detection. Bone metastases are best detected by MRI.