OBJECTIVE: Promptly establishing maintenance therapy could reduce morbidity and mortality in patients with bipolar disorder. Using a machine learning approach, we sought to evaluate whether lithium responsiveness (LR) is predictable using clinical markers. METHOD: Our data are the largest existing sample of direct interview-based clinical data from lithium-treated patients (n = 1266, 34.7% responders), collected across seven sites, internationally. We trained a random forest model to classify LR-as defined by the previously validated Alda scale-against 180 clinical predictors. RESULTS: Under appropriate cross-validation procedures, LR was predictable in the pooled sample with an area under the receiver operating characteristic curve of 0.80 (95% CI 0.78-0.82) and a Cohen kappa of 0.46 (0.4-0.51). The model demonstrated a particularly low false-positive rate (specificity 0.91 [0.88-0.92]). Features related to clinical course and the absence of rapid cycling appeared consistently informative. CONCLUSION: Clinical data can inform out-of-sample LR prediction to a potentially clinically relevant degree. Despite the relevance of clinical course and the absence of rapid cycling, there was substantial between-site heterogeneity with respect to feature importance. Future work must focus on improving classification of true positives, better characterizing between- and within-site heterogeneity, and further testing such models on new external datasets.

• Klíčová slova
• bipolar disorder, clinical prediction, lithium response, machine learning,
• MeSH
• antimanika terapeutické užití   MeSH
• bipolární porucha farmakoterapie   epidemiologie   MeSH
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• plocha pod křivkou MeSH
• poruchy iniciace a udržování spánku epidemiologie   MeSH
• pravidla klinického rozhodování * MeSH
• progrese nemoci MeSH
• rizikové faktory MeSH
• ROC křivka MeSH
• sloučeniny lithia terapeutické užití   MeSH
• strojové učení * MeSH
• věk při počátku nemoci MeSH
• výsledek terapie MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Názvy látek
• antimanika MeSH
• sloučeniny lithia MeSH

Background: The aim of this study was to evaluate left ventricular mechanical activation pattern by speckle tracking echocardiography (STE) as a predictor of response to cardiac resynchronization therapy (CRT) in patients with heart failure. Methods: Echocardiography was performed during no pacing, right ventricular pacing (RVP), biventricular pacing (BVP) and multipolar pacing (MPP) immediately after CRT implantation in 16 patients at a single centre. Seven patients were diagnosed as responders and 9 patients as non-responders after 6 months of standard CRT pacing. All had adequate short axis views, and 1 CRT responder and 2 CRT non-responders had limited longitudinal views. Results: Longitudinal and circumferential global strain (GS) and global strain rate (GSR) or their change analysis, did not yield any CRT response prediction. However, the longitudinal BVP/RVP GS ratio was significantly higher in the responder group (1.32 ± 0.2%, 2.0 ± 0.4% and 1.9 ± 0.4%), compared with the non-responder group (1.06 ± 0.2%, 1.1 ± 0.4% and 1.2 ± 0.4%) in the apical two-chamber, APLAX and four-chamber views, respectively. Similarly, the longitudinal BVP/RVP GSR at active systolic phase (GSRs) was significantly higher in the responder group (1.9 ± 0.9% and 1.7 ± 0.4%) compared with the non-responder group (1.0 ± 0.4% and 1.1 ± 0.2%) in the apical APLAX and four-chamber views, respectively. Measurements of the strain delay index showed predictive power regarding CRT response in non-paced patients. Conclusion: Post implantation, longitudinal BVP/RVP GS and GSRs ratios of 1.4% and above may be useful as a CRT response prediction tool. Furthermore, our findings support the usefulness of strain delay index prior to CRT implantation in non-paced patients.

• Klíčová slova
• Heart failure, cardiac resynchronization therapy, echocardiography, response prediction, speckle tracking,
• Publikační typ
• časopisecké články MeSH
• přehledy MeSH

Timely initiation of effective therapy is crucial for preventing disability in multiple sclerosis; however, treatment response varies greatly among patients. Comprehensive predictive models of individual treatment response are lacking. Our aims were: (i) to develop predictive algorithms for individual treatment response using demographic, clinical and paraclinical predictors in patients with multiple sclerosis; and (ii) to evaluate accuracy, and internal and external validity of these algorithms. This study evaluated 27 demographic, clinical and paraclinical predictors of individual response to seven disease-modifying therapies in MSBase, a large global cohort study. Treatment response was analysed separately for disability progression, disability regression, relapse frequency, conversion to secondary progressive disease, change in the cumulative disease burden, and the probability of treatment discontinuation. Multivariable survival and generalized linear models were used, together with the principal component analysis to reduce model dimensionality and prevent overparameterization. Accuracy of the individual prediction was tested and its internal validity was evaluated in a separate, non-overlapping cohort. External validity was evaluated in a geographically distinct cohort, the Swedish Multiple Sclerosis Registry. In the training cohort (n = 8513), the most prominent modifiers of treatment response comprised age, disease duration, disease course, previous relapse activity, disability, predominant relapse phenotype and previous therapy. Importantly, the magnitude and direction of the associations varied among therapies and disease outcomes. Higher probability of disability progression during treatment with injectable therapies was predominantly associated with a greater disability at treatment start and the previous therapy. For fingolimod, natalizumab or mitoxantrone, it was mainly associated with lower pretreatment relapse activity. The probability of disability regression was predominantly associated with pre-baseline disability, therapy and relapse activity. Relapse incidence was associated with pretreatment relapse activity, age and relapsing disease course, with the strength of these associations varying among therapies. Accuracy and internal validity (n = 1196) of the resulting predictive models was high (>80%) for relapse incidence during the first year and for disability outcomes, moderate for relapse incidence in Years 2-4 and for the change in the cumulative disease burden, and low for conversion to secondary progressive disease and treatment discontinuation. External validation showed similar results, demonstrating high external validity for disability and relapse outcomes, moderate external validity for cumulative disease burden and low external validity for conversion to secondary progressive disease and treatment discontinuation. We conclude that demographic, clinical and paraclinical information helps predict individual response to disease-modifying therapies at the time of their commencement.

• Klíčová slova
• disability, multiple sclerosis, precision medicine, prediction, relapses,
• MeSH
• algoritmy * MeSH
• databáze faktografické MeSH
• demografie MeSH
• dospělí MeSH
• imunosupresiva terapeutické užití   MeSH
• individualizovaná medicína metody   MeSH
• lidé MeSH
• mladý dospělý MeSH
• posuzování pracovní neschopnosti MeSH
• předpověď metody   MeSH
• prognóza MeSH
• progrese nemoci MeSH
• recidiva MeSH
• reprodukovatelnost výsledků MeSH
• rizikové faktory MeSH
• roztroušená skleróza diagnóza   farmakoterapie   MeSH
• výsledek terapie MeSH
• Check Tag
• dospělí MeSH
• lidé MeSH
• mladý dospělý MeSH
• mužské pohlaví MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• klinické zkoušky MeSH
• multicentrická studie MeSH
• Názvy látek
• imunosupresiva MeSH

A major challenge in cancer treatment is predicting clinical response to anti-cancer drugs on a personalized basis. Using a pharmacogenomics database of 1,001 cancer cell lines, we trained deep neural networks for prediction of drug response and assessed their performance on multiple clinical cohorts. We demonstrate that deep neural networks outperform the current state in machine learning frameworks. We provide a proof of concept for the use of deep neural network-based frameworks to aid precision oncology strategies.

• Klíčová slova
• DNN, deep neural networks, drug response prediction, machine learning, precision medicine,
• MeSH
• analýza přežití MeSH
• chemorezistence * MeSH
• deep learning * MeSH
• individualizovaná medicína metody   MeSH
• lidé MeSH
• nádorové buněčné linie MeSH
• nádory farmakoterapie   genetika   metabolismus   MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

BACKGROUND AND AIMS: [177Lu]Lu-PSMA-617 radioligand therapy (PSMA-RLT) is a new therapy for patients with metastatic castration-resistant prostate cancer (mCRPC). However, identification of reliable prognostic factors is hampered by heterogeneous treatment regimens applied in previous studies. Hence, we sought clinical factors able to predict response and survival to PSMA-RLT in a homogenous group of patients, all receiving 7400 MBq every 4 weeks. PATIENTS AND METHODS: Data of 61 patients (mean age 71.6 ± 6.9 years, median basal PSA 70.7 [range 1.0-4890 μg/L]), pretreated with abiraterone/enzalutamide (75.4%) and docetaxel/cabazitaxel (68.9%), received three cycles of PSMA-RLT (mean 7321 ± 592 MBq) at four weekly intervals and were analyzed retrospectively. General medical conditions and laboratory parameters of every patients were regularly assessed. Response to therapy was based on PSA levels 1 month after the 3rd cycle. Binary logistic regression test and Kaplan-Meier estimates were used to evaluate predictors and overall survival (OS). RESULTS: Forty-nine (80.3%) patients demonstrated a therapy response in terms of any PSA decline, while 21 (19.7%) patients showed increase or no changes in their PSA levels. Baseline hemoglobin (Hb) significantly predicted PSA reductions of ≥ 50% 4 weeks after receiving the 3rd PSMA-RLT (P = 0.01, 95% CI: 1.09-2.09) with an AUC of 0.68 (95% CI: 0.54-0.81). The levels of basal Hb and basal PSA were able to predict survival of patients, both P < 0.05 (relative risk 1.51 and 0.79, 95% CI: 1.09-2.09 and 0.43-1.46), respectively. In comparison to patients with reduced basal Hb, patients with normal basal Hb levels lived significantly longer (median survival not reached vs. 89 weeks, P = 0.016). Also, patients with basal PSA levels ≤ 650 μg/L had a significantly longer survival than patients with basal PSA levels > 650 μg/L (median survival not reached vs. 97 weeks, P = 0.031). Neither pretreatments with abiraterone/enzalutamide or docetaxel/cabazitaxel nor distribution of metastasis affected survival and rate of response to PSMA-RLT. CONCLUSION: Basal Hb level is an independent predictor for therapy response and survival in patients receiving PSMA-RLT every 4 weeks. Both baseline PSA ≤ 650 μg/L and normal Hb levels were associated with longer survival.

• Klíčová slova
• PSA, PSMA-RLT, Response prediction, Survival prediction, mCRPC,
• MeSH
• dipeptidy * terapeutické užití   MeSH
• heterocyklické sloučeniny monocyklické * terapeutické užití   MeSH
• lidé středního věku MeSH
• lidé MeSH
• lutecium MeSH
• nádory prostaty rezistentní na kastraci * farmakoterapie   radioterapie   MeSH
• prostatický specifický antigen MeSH
• radiofarmaka MeSH
• retrospektivní studie MeSH
• senioři MeSH
• výsledek terapie MeSH
• Check Tag
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Názvy látek
• dipeptidy * MeSH
• heterocyklické sloučeniny monocyklické * MeSH
• lutecium MeSH
• Pluvicto MeSH Prohlížeč
• prostatický specifický antigen MeSH
• PSMA-617 MeSH Prohlížeč
• radiofarmaka MeSH

This paper proposes development of optimized heterogeneous ensemble models for prediction of responses based on given sets of input parameters for wire electrical discharge machining (WEDM) processes, which have found immense applications in many of the present-day manufacturing industries because of their ability to generate complicated 2D and 3D profiles on hard-to-machine engineering materials. These ensembles are developed combining predictions of the three base models, i.e. random forest, support vector machine and ridge regression. These three base models are first framed utilizing the training datasets, providing predictions for all the responses under consideration. Based on these predictions, two optimization problems are formulated for each of the responses, while minimizing root mean squared error and mean absolute error, for subsequent development of two optimized ensembles whose predictions are the weighted sum of the predictions of the base models. The prediction performance of all the five models is ascertained through nine statistical metrics, after which a cumulative quality loss-based multi-response signal-to-noise (MRSN) ratio for each model is computed, for each of the responses, where a higher MRSN ratio indicates greater accuracy in prediction. This study is conducted using two experimental datasets of WEDM process. Overall, the optimized ensemble models having higher MRSN ratios than the base models are indicated to deliver better prediction accuracy.

• Klíčová slova
• Multi-response S/N ratio, Optimized heterogeneous ensemble, Prediction performance, Response, Wire electrical discharge machining,
• Publikační typ
• časopisecké články MeSH

Introduction: Patients with locally advanced rectal cancer (LARC) are undergoing neoadjuvant chemoradiotherapy (NCRT) prior to surgery. Although in some patients the NCRT is known to prevent local recurrence, it is also accompanied by side effects. Accordingly, there is an unmet need to identify predictive markers allowing to identify non-responders to avoid its adverse effects. We monitored circulating tumor DNA (ctDNA) as a potential liquid biopsy-based biomarker. We have investigated ctDNA changes plasma during the early days of NCRT and its relationship to the overall therapy outcome. Methods and Patients: The studied cohort included 36 LARC patients (stage II or III) undergoing NCRT with subsequent surgical treatment. We have detected somatic mutations in tissue biopsies taken during endoscopic examination prior to the therapy. CtDNA was extracted from patient plasma samples prior to therapy and at the end of the first week. In order to optimize the analytical costs of liquid-biopsy testing, we have utilized a two-level approach in which first a low-cost detection method of denaturing capillary electrophoresis was used followed by examination of initially negative samples by a high-sensitivity BEAMING assay. The ctDNA was related to clinical parameters including tumor regression grade (TRG) and TNM tumor staging. Results: We have detected a somatic mutation in 33 out of 36 patients (91.7%). Seven patients (7/33, 21.2%) had ctDNA present prior to therapy. The ctDNA positivity before treatment reduced post-operative disease-free survival and overall survival by an average of 1.47 and 1.41 years, respectively (p = 0.015, and p = 0.010). In all patients, ctDNA was strongly reduced or completely eliminated from plasma by the end of the first week of NCRT, with no correlation to any of the parameters analyzed. Conclusions: The baseline ctDNA presence represented a statistically significant negative prognostic biomarker for the overall patient survival. As ctDNA was reduced indiscriminately from circulation of all patients, dynamics during the first week of NCRT is not suited for predicting the outcome of LARC. However, the general effect of rapid ctDNA disappearance apparently occurring during the initial days of NCRT is noteworthy and should further be studied.

• Klíčová slova
• biomarker, circulating tumor ctDNA, neoadjuvant chemoradiotherapy, prediction, prognosis, rectal cancer, response,
• Publikační typ
• časopisecké články MeSH

CONTEXT: First-generation somatostatin receptor ligands (fg-SRLs) represent the mainstay of medical therapy for acromegaly, but they provide biochemical control of disease in only a subset of patients. Various pretreatment biomarkers might affect biochemical response to fg-SRLs. OBJECTIVE: To identify clinical predictors of the biochemical response to fg-SRLs monotherapy defined as biochemical response (insulin-like growth factor (IGF)-1 ≤ 1.3 × ULN (upper limit of normal)), partial response (>20% relative IGF-1 reduction without normalization), and nonresponse (≤20% relative IGF-1 reduction), and IGF-1 reduction. DESIGN: Retrospective multicenter study. SETTING: Eight participating European centers. METHODS: We performed a meta-analysis of participant data from 2 cohorts (Rotterdam and Liège acromegaly survey, 622 out of 3520 patients). Multivariable regression models were used to identify predictors of biochemical response to fg-SRL monotherapy. RESULTS: Lower IGF-1 concentration at baseline (odds ratio (OR) = 0.82, 95% confidence interval (CI) 0.72-0.95 IGF-1 ULN, P = .0073) and lower bodyweight (OR = 0.99, 95% CI 0.98-0.99 kg, P = .038) were associated with biochemical response. Higher IGF-1 concentration at baseline (OR = 1.40, (1.19-1.65) IGF-1 ULN, P ≤ .0001), the presence of type 2 diabetes (oral medication OR = 2.48, (1.43-4.29), P = .0013; insulin therapy OR = 2.65, (1.02-6.70), P = .045), and higher bodyweight (OR = 1.02, (1.01-1.04) kg, P = .0023) were associated with achieving partial response. Younger patients at diagnosis are more likely to achieve nonresponse (OR = 0.96, (0.94-0.99) year, P = .0070). Baseline IGF-1 and growth hormone concentration at diagnosis were associated with absolute IGF-1 reduction (β = 0.90, standard error (SE) = 0.02, P ≤ .0001 and β = 0.002, SE = 0.001, P = .014, respectively). CONCLUSION: Baseline IGF-1 concentration was the best predictor of biochemical response to fg-SRL, followed by bodyweight, while younger patients were more likely to achieve nonresponse.

• Klíčová slova
• acromegaly, biochemical response, first-generation somatostatin receptor ligands,
• MeSH
• akromegalie krev   diagnóza   farmakoterapie   MeSH
• biologické markery analýza   metabolismus   MeSH
• biomarkery farmakologické * analýza   metabolismus   MeSH
• cyklické peptidy terapeutické užití   MeSH
• dospělí MeSH
• insulinu podobný růstový faktor I metabolismus   MeSH
• kohortové studie MeSH
• lidé středního věku MeSH
• lidé MeSH
• lidský růstový hormon krev   MeSH
• ligandy MeSH
• multivariační analýza MeSH
• oktreotid terapeutické užití   MeSH
• prognóza MeSH
• receptory somatostatinu agonisté   MeSH
• retrospektivní studie MeSH
• somatostatin analogy a deriváty   terapeutické užití   MeSH
• teoretické modely * MeSH
• výsledek terapie MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• metaanalýza MeSH
• multicentrická studie MeSH
• práce podpořená grantem MeSH
• Geografické názvy
• Evropa MeSH
• Názvy látek
• biologické markery MeSH
• biomarkery farmakologické * MeSH
• cyklické peptidy MeSH
• insulinu podobný růstový faktor I MeSH
• lanreotide MeSH Prohlížeč
• lidský růstový hormon MeSH
• ligandy MeSH
• oktreotid MeSH
• receptory somatostatinu MeSH
• somatostatin MeSH

BACKGROUND: The anti-epidermal growth factor receptor (EGFR) monoclonal antibodies (moAbs) cetuximab or panitumumab are administered to colorectal cancer (CRC) patients who harbor wild-type RAS proto-oncogenes. However, a percentage of patients do not respond to this treatment. In addition to mutations in the RAS genes, mutations in other genes, such as BRAF, PI3KCA, or PTEN, could be involved in the resistance to anti-EGFR moAb therapy. METHODS: In order to develop a comprehensive approach for the detection of mutations and to eventually identify other genes responsible for resistance to anti-EGFR moAbs, we investigated a panel of 21 genes by parallel sequencing on the Ion Torrent Personal Genome Machine platform. We sequenced 65 CRCs that were treated with cetuximab or panitumumab. Among these, 37 samples were responsive and 28 were resistant. RESULTS: We confirmed that mutations in EGFR-pathway genes (KRAS, NRAS, BRAF, PI3KCA) were relevant for conferring resistance to therapy and could predict response (p = 0.001). After exclusion of KRAS, NRAS, BRAF and PI3KCA combined mutations could still significantly associate to resistant phenotype (p = 0.045, by Fisher exact test). In addition, mutations in FBXW7 and SMAD4 were prevalent in cases that were non-responsive to anti-EGFR moAb. After we combined the mutations of all genes (excluding KRAS), the ability to predict response to therapy improved significantly (p = 0.002, by Fisher exact test). CONCLUSIONS: The combination of mutations at KRAS and at the five gene panel demonstrates the usefulness and feasibility of multigene sequencing to assess response to anti-EGFR moAbs. The application of parallel sequencing technology in clinical practice, in addition to its innate ability to simultaneously examine the genetic status of several cancer genes, proved to be more accurate and sensitive than the presently in use traditional approaches.

• MeSH
• cetuximab farmakologie   terapeutické užití   MeSH
• dospělí MeSH
• erbB receptory antagonisté a inhibitory   MeSH
• humanizované monoklonální protilátky farmakologie   terapeutické užití   MeSH
• kolorektální nádory diagnóza   farmakoterapie   genetika   MeSH
• lidé středního věku MeSH
• lidé MeSH
• monoklonální protilátky farmakologie   terapeutické užití   MeSH
• nádorové biomarkery genetika   MeSH
• panitumumab MeSH
• prediktivní hodnota testů MeSH
• protinádorové látky farmakologie   terapeutické užití   MeSH
• senioři nad 80 let MeSH
• senioři MeSH
• výsledek terapie MeSH
• Check Tag
• dospělí MeSH
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři nad 80 let MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH
• Názvy látek
• cetuximab MeSH
• EGFR protein, human MeSH Prohlížeč
• erbB receptory MeSH
• humanizované monoklonální protilátky MeSH
• monoklonální protilátky MeSH
• nádorové biomarkery MeSH
• panitumumab MeSH
• protinádorové látky MeSH

Accurate prediction of early treatment response to systemic therapy (ST) with tyrosine kinase inhibitors (TKI) in patients with metastatic renal cell carcinoma (mRCC) could help avoid ineffective and expensive treatment with serious side effects. Neither RECIST v.1.1 nor Choi criteria successfully discriminate between patients with mRCC who received ST having a short or long time to progression (TTP). There is no biomarker, which is able to predict early therapeutic response to TKIs application in patients with mRCC. The goal of our study was to investigate the potential of apparent diffusion coefficient (ADC) of diffusion-weighted imaging (DWI) of MRI in prediction of early therapeutic response to ST with pazopanib in patients with mRCC. The retrospective study enrolled 32 adult patients with conventional mRCC who received pazopanib (mean duration-7.5 ± 3.45). The mean duration of follow-up was 11.85 ± 4.34 months. In all patients as baseline examination and 1 month after treatment, 1.5T MRI including DWI sequence was performed followed by ADC measurement of the main renal lesion. For assessment of the therapeutic response, RECIST 1.1 is used. Partial response (PR), stable disease (SD) and progressive disease (PD) were observed in 12 (37.50%), 10 (31.25%) and 10 (31.25%) cases with mean TTP of 10.33 ± 2.06 months (95% confidence interval, CI = 9.05-11.61), 7.40 ± 2.50 months (95% CI = 5.61-9.19) and 4.20 ± 1.99 months (95% CI = 2.78-5.62) accordingly (p < 0.05). There was no difference in change of main lesions' longest size 1 month after ST in patients with PR, SD and PD. Comparison of mean ADC values before and 1 month after systemic treatment showed significant decrease by 19.11 ± 10.64% (95% CI = 12.35-25.87) and by 7.66 ± 6.72% (95% CI = 2.86-12.47) in subgroups with PR and SD, respectively (p < 0.05). There was shorter TTP in patients with mRCC if ADC of the main renal lesion 1 month after the ST increased from the baseline less than 1.73% compared to patients with ADC levels above this threshold: 5.29 ± 3.45 versus 9.50 ± 2.04 months accordingly (p < 0.001). Overall, our findings highlighted the use of ADC as a predictive biomarker for early therapeutic response assessment. Use of ADC will be effective and useful for reliable prediction of responders and non-responders to systemic treatment with pazopanib.

• Klíčová slova
• Apparent diffusion coefficient, Diffusion-weighted imaging, Early response, Imaging biomarker, MRI, Prediction, Progress, Renal cell carcinoma, Systemic treatment, Targeted therapy, Tyrosine kinase inhibitor,
• MeSH
• difuzní magnetická rezonance metody   MeSH
• indazoly MeSH
• inhibitory angiogeneze terapeutické užití   MeSH
• Kaplanův-Meierův odhad MeSH
• karcinom z renálních buněk diagnostické zobrazování   farmakoterapie   mortalita   patologie   MeSH
• ledviny diagnostické zobrazování   MeSH
• lidé středního věku MeSH
• lidé MeSH
• nádory ledvin diagnostické zobrazování   farmakoterapie   mortalita   patologie   MeSH
• pyrimidiny terapeutické užití   MeSH
• retrospektivní studie MeSH
• ROC křivka MeSH
• senioři MeSH
• sulfonamidy terapeutické užití   MeSH
• výsledek terapie MeSH
• zdraví dobrovolníci pro lékařské studie MeSH
• Check Tag
• lidé středního věku MeSH
• lidé MeSH
• mužské pohlaví MeSH
• senioři MeSH
• ženské pohlaví MeSH
• Publikační typ
• časopisecké články MeSH
• klinické zkoušky MeSH
• Názvy látek
• indazoly MeSH
• inhibitory angiogeneze MeSH
• pazopanib MeSH Prohlížeč
• pyrimidiny MeSH
• sulfonamidy MeSH