Boamente: A Natural Language Processing-Based Digital Phenotyping Tool for Smart Monitoring of Suicidal Ideation.

People at risk of suicide tend to be isolated and cannot share their thoughts. For this reason, suicidal ideation monitoring becomes a hard task. Therefore, people at risk of suicide need to be monitored in a manner capable of identifying if and when they have a suicidal ideation, enabling professionals to perform timely interventions. This study aimed to develop the Boamente tool, a solution that collects textual data from users' smartphones and identifies the existence of suicidal ideation. The solution has a virtual keyboard mobile application that passively collects user texts and sends them to a web platform to be processed. The platform classifies texts using natural language processing and a deep learning model to recognize suicidal ideation, and the results are presented to mental health professionals in dashboards. Text classification for sentiment analysis was implemented with different machine/deep learning algorithms. A validation study was conducted to identify the model with the best performance results. The BERTimbau Large model performed better, reaching a recall of 0.953 (accuracy: 0.955; precision: 0.961; F-score: 0.954; AUC: 0.954). The proposed tool demonstrated an ability to identify suicidal ideation from user texts, which enabled it to be experimented with in studies with professionals and their patients.

Chronic kidney disease and dipstick proteinuria are risk factors for stent thrombosis in patients with myocardial infarction.

BACKGROUND: Kidney failure (stage 5 chronic kidney disease [CKD]) is an independent risk factor for stent thrombosis (ST). Moderate (stage 3-4) CKD and proteinuria are both associated with adverse cardiovascular events, including worse outcomes after myocardial infarction (MI). Whether moderate CKD and proteinuria increase the risk of ST after MI is not known. This study evaluated the risk of ST associated with moderate CKD and dipstick proteinuria. METHODS: We retrospectively analyzed clinical and laboratory data from 956 non-stage 5 CKD patients who were admitted with MI and received intracoronary stenting. Clinical follow-up was collected at 1 year for definite or probable ST, as well as for all-cause mortality, nonfatal MI or death, and target vessel revascularization or coronary artery bypass graft surgery. RESULTS: After adjustment for multiple clinical and biochemical covariates, patients with both estimated glomerular filtration rate (GFR) of 15 to 59 mL min(-1) 1.73 m(-2) and > or =30 mg/dL dipstick proteinuria had increased cumulative incidence of ST (hazard rate [HR] 3.69, 95% CI 1.54-8.89), all-cause mortality (HR 2.68, 95% CI 1.34-5.37), and nonfatal MI or death (HR 3.20, 95% CI 1.77-5.81) at 1 year. In addition, estimated GFR of 15 to 59 mL min(-1) 1.73 m(-2) was a significant independent predictor of ST (HR 2.61, 95% CI 1.33-5.10). Dipstick proteinuria > or =30 mg/dL was associated with a trend toward increased risk for all outcomes. CONCLUSIONS: In an acute MI population, moderate CKD was identified as a novel prognostic marker for ST. In addition, patients with both decreased GFR and proteinuria had higher incidences of all-cause mortality and nonfatal MI or death than patients with either condition alone.

Incidence of coronary stent thrombosis based on academic research consortium definitions.

Stent thrombosis occurs infrequently after drug-eluting stent (DES) placement, but concerns have surfaced that identification of stent thrombosis based solely on angiography may underestimate the true incidence of this complication. The purpose of this study was to compare rates of stent thrombosis using Academic Research Consortium (ARC) definitions. From April 2002 to February 2005, bare-metal stents (BMSs) and DESs were placed at Wake Forest University Baptist Medical Center. Rates of ARC definite, probable, and possible stent thrombosis were evaluated. Overall, definite stent thrombosis occurred in 1.4% of BMSs and 1.1% of DESs (p = 0.47); probable stent thrombosis, in 1.0% of BMSs and 0.9% of DESs (p = 0.81); definite plus probable stent thrombosis, in 2.3% of BMSs and 1.9% of DESs (p = 0.48); and possible stent thrombosis, in 6.8% of BMSs and 3.5% of DESs (p <0.001). Rates of definite late (31 days to 1 year) and very late (>1 year) stent thrombosis were 0.9% for BMSs and 0.06% for DESs (p <0.001) and 0.16% for BMSs and 0.56% for DESs, respectively (p = 0.13). Rates of definite plus probable and late and very late stent thrombosis were 1.1% for BMSs and 0.19% for DESs (p <0.001) and 0.40% for BMSs and 0.68% for DESs, respectively (p = 0.31). Rates of possible stent thrombosis increased significantly for each thrombosis interval. In conclusion, rates of stent thrombosis using the proposed ARC definition differed by stent type, definition of stent thrombosis, and thrombosis interval. Use of the ARC probable stent thrombosis paralleled rates of definite stent thrombosis alone, but partially masked the occurrence of late (>1 year) stent thrombosis in DESs compared with BMSs.

Comparison of drug-eluting versus bare metal stents on later frequency of acute myocardial infarction and death.

In clinical trials of highly selected patients, drug-eluting stents (DESs) decreased restenosis but not the rate of acute myocardial infarction (AMI) or death. Whether DES use has an affect on the rate of AMI or death in unselected patients is uncertain. Bare metal stents (BMSs) were placed in 1,164 consecutive patients in the year before the introduction of DESs. DESs were subsequently placed in 1,285 consecutive comparable patients at Wake Forest Baptist Medical Center. Early and late clinical outcomes were compared. Propensity score analysis was used to adjust outcomes for baseline differences. Patient and procedural characteristics of the 2 groups were similar, with an overall incidence of 72% for acute coronary syndromes (p = NS). At 9 months, target vessel revascularization (2.8% vs 8.6%, p <0.001), AMI (3.7% vs 4.7%, p = 0.257), and death (4.9% vs 7.1%, p = 0.030) were lower in the DES group than in the BMS group. Propensity score-adjusted Cox proportional hazard ratios for DES versus BMS at 9 months were 0.71 (95% confidence interval 0.42 to 1.19) for AMI, 0.56 (95% confidence interval 0.36 to 0.87) for death, and 0.60 (95% confidence interval 0.42 to 0.86) for the combined end point of AMI or death. In conclusion, in this single-center observational study, use of DESs in consecutive unselected patients, most of whom would not have been eligible for inclusion in the randomized trials of DES versus BMS, was associated with lower AMI and death rates than in a comparable group of patients treated with BMSs in mid-term (9-month) follow-up.

Cost-effectiveness of drug-eluting stents versus bare metal stents in clinical practice.

BACKGROUND: Drug-eluting stents (DES) reduce the need for repeat target revascularization (TVR) compared with bare metal stents (BMS) but are more costly. The objective was to evaluate the cost-effectiveness of DES versus BMS. METHODS AND RESULTS: We evaluated clinical outcomes and costs of care over 3 years in 1147 undergoing BMS before the availability of DES and 1247 DES patients at Wake Forest University Baptist Medical Center from 2002 to 2005. Costs for index stenting, TVR, and clopidogrel use were assessed. The 2 groups were well matched for baseline characteristics. Index stenting costs were $1846 higher per patient for DES versus BMS ($1737 more to $1950 more). At 3 years, absolute TVR rates were 15.2 per 100 DES patients and 24.1 per 100 BMS patients, and as a result, cumulative TVR-related costs were $2065 less per patient for DES versus BMS ($3001 less to $1134 less). Including the cost of clopidogrel, the incremental cost-effectiveness ratio per TVR avoided with DES was $4731 through 1 year, $4703 through 2 years, and $6379 through 3 years. CONCLUSIONS: At 3 years, the higher index cost of DES versus BMS was completely offset by lower TVR-related costs. However, because of extended clopidogrel use for DES, the incremental cost-effectiveness ratio per TVR avoided ranged from $4703 to $6379 over 3 years. These unadjusted observational findings provide support for the continued use of DES in routine practice but highlight the important impact of prolonged dual antiplatelet use on the cost-effectiveness of this technology.

Target lesion revascularization after bare-metal or drug-eluting stents: clinical presentations and outcomes.

OBJECTIVE: We sought to examine the clinical presentations and subsequent clinical outcomes of patients undergoing target lesion revascularization (TLR) after either bare-metal stent (BMS) or drug-eluting stent (DES) placement. BACKGROUND: The widely held notion that BMS TLR is benign has recently been challenged. While DES substantially reduce TLR, little is known about the clinical syndromes accompanying DES TLR and the long-term clinical outcomes after TLR. METHODS: The clinical syndrome at the time of hospitalization when TLR was performed and subsequent clinical outcomes after TLR were assessed in 1,147 BMS patients and 1,246 DES patients who were followed for 3 years. Patients were considered to have TLR when repeat target lesion PCI was required including those with myocardial infarction (MI) and stent thrombosis. RESULTS: At 3 years, the overall incidence of TLR was higher after BMS compared to DES 98/1,147 (9.2%) vs. 56/1,246 (4.5%); p < 0.001. The clinical presentations at the time of TLR were not always benign with non-STelevation myocardial infarction (N-STEMI) or STEMI in 25% of BMS vs. 34% DES; p = 0.217. The risk of non-fatal MI or death outcomes over 3 years were significantly worse in those with TLR compared to those without TLR; hazard ratio (HR) 2.65 (2.00-3.52), independent of stent type. CONCLUSIONS: The clinical presentation at the time of TLR is not always a benign clinical event and identifies a subgroup of stent-treated patients at high risk for non-fatal MI or death in the 3 years following the index percutaneous coronary intervention, independent of stent type.

Effect of length and diameter of drug-eluting stents versus bare-metal stents on late outcomes.

BACKGROUND: The risk of restenosis and other adverse cardiac events with bare-metal stents (BMS) is increased with smaller stent diameters and longer stent lengths. Drug-eluting stents (DES) may reduce this effect in select patients; however, whether this benefit occurs in high-risk lesions and patients in routine practice is not clear. METHODS AND RESULTS: Clinical outcomes (target-vessel revascularization [TVR], stent thrombosis, nonfatal myocardial infarction [MI], and cardiac death) at 2 years stratified by stented length and diameter were compared in 949 consecutive patients who received BMS and 1236 consecutive and comparable patients who received DES for single lesions. The longest tertile of BMS (>23 mm) was associated with increased hazard of TVR, ST, and nonfatal MI or death compared with shorter tertiles of BMS, which was abolished by DES. DES compared with BMS was independently associated with a lower hazard of TVR (HR, 0.34 [0.20 to 0.58]) and nonfatal MI or death (HR, 0.60 [0.39 to 0.92]) in the longest length tertile (>23 mm). No clear association of stented tertile diameter and clinical outcomes for either stent type was observed. However, DES compared with BMS was independently associated with a lower hazard of TVR for all diameter tertiles, and a lower hazard of nonfatal MI or death (0.66 [0.44 to 0.99]) in the largest diameter tertile (>3.4 mm). CONCLUSIONS: Independent of adverse patient and lesion characteristics, DES demonstrated significantly lower hazard of TVR and nonfatal MI or death at 2 years compared with BMS within the longest stented lengths (>23 mm) and largest diameters (>3.4 mm).

3-year comparison of drug-eluting versus bare-metal stents.

OBJECTIVES: The aim of this study was to compare 3-year cumulative outcomes to landmark second- and third-year outcomes with the routine use of drug-eluting stents (DES) (>75% "off-label") with a comparable group treated with bare-metal stents (BMS). BACKGROUND: Long-term safety concerns after "off-label" DES use persist, despite recent 2-year data showing comparable safety to BMS use. METHODS: Clinical outcomes (nonfatal myocardial infarction, all-cause mortality) were assessed in 1,147 consecutive patients who received a BMS in the year before the introduction of DES at Wake Forest University Baptist Medical Center and 1,246 consecutive patients that received a DES after it became our routine choice with equivalent complete 3-year follow-up. RESULTS: Stents were used for "off-label" indications in 80% of DES patients. At 3 years, the hazard ratio for DES compared with BMS for cumulative target vessel revascularization was 0.65 (95% confidence interval [CI]: 0.51 to 0.82), nonfatal myocardial infarction or death was 0.85 (95% CI: 0.71 to 1.03), and all-cause mortality 0.80 (95% CI: 0.64 to 1.01). The DES clinical benefits occurred entirely within the first year, with similar rates of these clinical end points in the second and third year. The cumulative hazard ratio of stent thrombosis DES compared with BMS was 1.07 (95% CI: 0.57 to 2.01), with similar rates of stent thrombosis in the third year (p = 0.70). CONCLUSIONS: The routine clinical use of DES for "off-label" indications was associated with lower clinical end points at 3 years than treatment with BMS in a comparable group of patients, with similar cumulative rates of stent thrombosis. There was no evidence of late "catch-up" of adverse DES events.

"Off-label" stent therapy 2-year comparison of drug-eluting versus bare-metal stents.

OBJECTIVE: The aim was to compare 2-year outcomes with the routine use of drug-eluting stents (DES) (>75% "off-label") with a comparable group treated with bare-metal stents (BMS). BACKGROUND: Safety concerns >1 year from implantation have been raised about DES used "off-label." There are limited data comparing DES and BMS in "off-label" patients. METHODS: Clinical outcomes (nonfatal myocardial infarction [MI], all-cause mortality) were assessed in 1,164 consecutive patients who received BMS in the year before introduction of DES at Wake Forest University Baptist Medical Center and 1,285 consecutive patients who received DES after it became our routine choice. "On-label" stent use was defined as treatment for a single de novo lesion <30 mm, without recent MI or other major illnesses. RESULTS: At 2 years, the hazard ratio for DES compared with BMS for nonfatal MI or death was 0.77 (95% confidence interval [CI] 0.62 to 0.95), for all-cause mortality 0.71 (0.54 to 0.92), and stent thrombosis (ST) 0.97 (0.49 to 1.91). "On-label" stent procedures were associated with lower risk of MI, death, and ST than "off-label" stent procedures. For "off-label" stent procedures, the hazard ratio for DES compared with BMS for nonfatal MI or death was 0.78 (95% CI 0.62 to 0.98), all-cause mortality 0.72 (0.54 to 0.94), and ST 0.91 (0.46 to 1.80). The hazard of nonfatal MI or death was similar or lower for DES than BMS in high-risk subgroups, including renal failure and recent MI. CONCLUSIONS: The routine clinical use of drug-eluting stents for "off-label" indications was associated with lower nonfatal MI and death at 2 years than in a comparable group of patients treated with BMS.

Culprit vessel PCI versus traditional cath and PCI for STEMI.

OBJECTIVE: To compare door-to-balloon times with culprit vessel percutaneous coronary intervention (PCI) as initial treatment for ST-elevation myocardial infarction (STEMI) to traditional complete coronary angiography followed by PCI for treatment of STEMI. BACKGROUND: Shorter door-to-balloon time for STEMI treatment is associated with better outcomes, and is generally achieved by shortening the door-to-vascular access time. Whether procedural improvements can shorten the vascular access-to-balloon time has not been examined. METHODS: Door-to-balloon times were assessed in 50 consecutive patients who underwent initial PCI of the culprit vessel for STEMI at Wake Forest University Baptist Medical Center, and in 85 consecutive patients who underwent traditional coronary angiography followed by PCI for STEMI. RESULTS: Procedural success was 100% in both groups. Door-to-balloon times were 66 +/- 20 minutes for culprit PCI vs. 79 +/- 28 minutes for traditional PCI, p < 0.001, due to shorter vascular access-to-balloon time, 11 +/- 8 minutes for culprit PCI vs. 18 +/- 8 minutes for traditional PCI, p < 0.001. 92% of the culprit PCI group had a door-to-balloon time < 90 minutes, compared to 76% in the traditional group, p = 0.023. Subsequent planned revascularization procedures were infrequent and similar in both groups. CONCLUSIONS: In this small pilot study, performing PCI of the culprit vessel for STEMI as initial treatment resulted in a decrease in the door-to-balloon time compared to traditional coronary angiography followed by PCI without compromising subsequent cardiac care. Whether broader utilization of this strategy will result in beneficial outcomes remains to be determined.

Trends in vascular complications after diagnostic cardiac catheterization and percutaneous coronary intervention via the femoral artery, 1998 to 2007.

OBJECTIVES: This study sought to evaluate trends in vascular complications after diagnostic cardiac catheterization (CATH) and percutaneous coronary intervention (PCI) from the femoral artery from 1998 to 2007. BACKGROUND: Vascular complications have been recognized as an important factor in morbidity after CATH and PCI. Whether strategies to reduce vascular complications performed from the femoral artery in the past decade have improved the safety of these procedures, however, is uncertain. METHODS: A total of 35,016 consecutive diagnostic cardiac catheterization (n = 20,777) and percutaneous coronary intervention procedures (n = 14,239) performed via a femoral access at a single site (Wake Forest University Baptist Medical Center) between 1998 and 2007 were evaluated. Annual rates of vascular complications were evaluated. Covariate effects on the risk of vascular complications were evaluated by logistic regression and risk-adjusted trend analysis. RESULTS: Overall, the incidence of any vascular complication decreased significantly for CATH, 1.7% versus 0.2%, and PCI, 3.1% versus 1.0%, from 1998 to 2007, both p < 0.001 for trend. Favorable trends in procedural covariates affecting vascular complications were mainly responsible for the decrease in the incidence of vascular complications, including fewer closure device failures and use of smaller sheath sizes. CONCLUSIONS: In this large, single-center, contemporary observational study, the safety of CATH and PCI performed from the femoral artery improved significantly from 1998 to 2007. Reductions in the prevalence of adverse procedural factors contributed to the decrease in the incidence of vascular complications, suggesting that strategies to reduce vascular complications can be effective in improving the safety of these procedures.

Propensity score analysis of vascular complications after diagnostic cardiac catheterization and percutaneous coronary intervention using thrombin hemostatic patch-facilitated manual compression.

OBJECTIVES: To evaluate the adjusted risk of vascular complications after thrombin hemostasis patch-facilitated manual compression (THP-MC) for femoral artery access site management. BACKGROUND: Thrombin hemostatic patches shorten time to hemostasis after cardiac procedures involving femoral artery access, but whether these patches are as safe as manual compression remains uncertain. METHODS: THP-MC (D-Stat Dry, Vascular Solutions, Minneapolis, Minnesota) was used in 3,464 consecutive patients including 2,464 diagnostic cardiac catheterizations (CATH) and 1,000 percutaneous coronary intervention procedures (PCI) performed via a femoral access at a single site (WFUBMC). A total of 4,371 procedures including 2,956 CATH and 1,415 PCI performed prior to use of THP-MC, and treated with manual compression, served as the control group. Ambulation was permitted 2 to 3 hours after THP-MC, and 3 to 8 hours after MC. Propensity to receive a THP was calculated, and adjusted in-hospital outcomes evaluated. RESULTS: Time to hemostasis was similar for THP-MC (13.0 +/- 3.3 min) compared to MC (14.4 +/- 5.7 min), p = 0.51 for CATH, and was shorter for THP-MC (14.2 +/- 5.4 minutes) compared to MC (20.1 +/- 5.4 min), p <0.001, for PCI. Overall, the unadjusted incidence of any vascular complication (VC) was 0.6+/- for THP-MC and 1.0% for manual compression, p = 0.036. The propensity score-adjusted odds ratio for any VC comparing THP-MC to manual compression was 0.58 (0.34 to 0.99) for all procedures, 0.42 (0.20 to 0.87) for diagnostic procedures and 0.86 (0.39 to 1.88) for PCI. CONCLUSIONS: In this large, single-center, contemporary observational study, use of THP-MC shortened manual compression time for PCI procedures, permitted early ambulation and was as safe as conventional manual compression.

Vascular complications in women after catheterization and percutaneous coronary intervention 1998-2005.

BACKGROUND: Previous studies have indicated that women experience more vascular complications after cardiac catheterization (CATH) and percutaneous coronary intervention (PCI) than men. Whether awareness of this gender risk or implementation of strategies to reduce the overall incidence of vascular complications has had an effect on the incidence of vascular complications in women is unknown. METHODS: A total of 31,035 consecutive diagnostic CATH (n = 18,467) and PCI procedures (n = 12,568) performed via femoral access at a single site (WFUBMC) between 1998 and 2005 were evaluated. The relative incidence of vascular complications was evaluated by logistic regression models adjusted for baseline covariates. RESULTS: For the entire study period, the unadjusted incidence of any vascular complication was 2.0% for women and 1.0% for men; p < 0.05. The risk-adjusted odds ratio for any vascular complication comparing women to men for the entire study period was 1.75 (95% CI 1.37-2.23) for all procedures, 1.66 (1.17-2.36) for CATH, and 1.83 (1.32-2.54) for PCI. However, the incidence of vascular complications fell for women during the study period; p < 0.001 for trend. In 2005, the adjusted relative risk of any vascular complications in women was not significantly higher than for men OR 0.98 (0.33-2.87). CONCLUSION: In this large, single-center, contemporary observational study, female gender was the strongest independent predictor of any vascular complication after CATH and PCI. However, the incidence of vascular complications in women decreased over the 8-year study period, and the increased risk of vascular complications in women compared to men was no longer present in 2005.

Vascular complications with newer generations of angioseal vascular closure devices.

OBJECTIVES: To evaluate the safety and efficacy of newer generations of a single vascular closure device (VCD), Angioseal, compared to contemporaneous manual compression. BACKGROUND: Previous assessment of VCD safety and efficacy has been based primarily on outcomes associated with the original VCD. Few data exist comparing safety and efficacy of modifications of the original VCDs. METHODS: We evaluated in-hospital outcomes of patients undergoing diagnostic cath and percutaneous coronary intervention at a single center: 3,898 with manual compression and 3,898 with the Angioseal VCD. Three generations of the Angioseal device were studied: Generation 1, 7/97-4/00; Generation 2, 5/00-6/02; and Generation 3, 7/02-12/03. Propensity analysis was used to match patients within each generation for clinical and procedural covariates. RESULTS: Closure success was 98.5% for Generation 1, 98.6% for Generation 2, and 98.1% for Generation 3, P = NS. The odds ratio for any vascular complication comparing Angioseal to manual compression was 0.92 (0.42-2.01) for Generation 1; 0.83 (0.49-1.41) for Generation 2; and 0.75 (0.32-1.77) for Generation 3. Multivariate logistic regression identified closure success and Angioseal device Generation 3 versus Generation 1 as predictive of reduced vascular complications during the entire study period. CONCLUSION: These data indicate that the newest generation of the Angioseal VCD is at least as effective as the original device. Moreover, use of the Angioseal VCD was associated with vascular complications similar to or lower than vascular complications following manual compression for each generation of Angioseal device analyzed.

Propensity score analysis of vascular complications after diagnostic cardiac catheterization and percutaneous coronary intervention 1998-2003.

OBJECTIVES: To evaluate the adjusted risk of vascular complications after manual compression and vascular closure devices for femoral artery access site management in a large contemporary cohort, using propensity score analysis. BACKGROUND: Vascular closure devices (VCD) allow early ambulation after cardiac procedures involving femoral artery access, but whether the benefit of use of vascular closure devices (VCD) is offset by reduced safety in contemporary practice remains uncertain. METHODS: Twenty one thousand eight hundred and forty one consecutive diagnostic cardiac catheterization (n = 13,124) and percutaneous coronary intervention procedures (n = 8,717) performed via a femoral access at a single site (WFUBMC) between 1998 and 2003 were evaluated. VCD's were used based on operator preference. Propensity to receive a vascular closure device (VCD) was calculated. The relative incidence of vascular complications was evaluated by logistic regression models, using the propensity score as a covariate. RESULTS: Overall, the unadjusted incidence of any vascular complication was 1.3% for VCD use and 1.4% for manual compression, p = NS. The propensity score-adjusted odds ratio for any vascular complication comparing VCD (n = 8,707) to manual compression (n = 13,034) was 0.86 (0.67-1.11) for all procedures, 0.80 (0.53-1.21) for diagnostic procedure, and 0.90 (0.65-1.26) for interventional procedures. CONCLUSIONS: In this large single-center, contemporary observational study, the risk-adjusted occurrence of vascular complications following VCD use for femoral artery access management is not increased by VCD use. Thus, in the current era, the benefit of VCD use is not offset by reduced safety.