Fractional Flow Reserve Cardio-Oncology Effects on Inpatient Mortality, Length of Stay, and Cost Based on Malignancy Type: Machine Learning Supported Nationally Representative Case-Control Study of 30 Million Hospitalizations
Abstract
:1. Introduction
2. Materials and Methods
2.1. Data Source
2.2. Study Design
2.3. Descriptive and Bivariable Statistical Analysis
2.4. Regression Statistical Analysis, Machine Learning Analysis, and Model Optimization
2.5. Machine Learning-Augmented Propensity Score Adjusted Multivariable Regression (ML-PSr)
2.6. Stratification and Sub-Group Analysis
2.7. Model Validation, Reporting, and Analytic Software
3. Results
3.1. Descriptive Statistics
3.2. Multivariable Regression
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Mehta, S.; Cannon, C.; Fox, K.; Wallentin, L.; Boden, W.E.; Spacek, R.; Widimsky, P.; McCullough, P.A.; Hunt, D.; Braunwald, E.; et al. Routine vs. selective invasive strategies in patients with acute coronary syndromes: A collaborative meta-analysis of randomized trials. JAMA 2005, 293, 2908–2917. [Google Scholar] [CrossRef] [PubMed]
- Katritsis, D.G.; Ioannidis, J.P. Percutaneous coronary intervention versus conservative therapy in nonacute coronary artery disease: A meta-analysis. Circulation 2005, 111, 2906–2912. [Google Scholar] [CrossRef] [PubMed]
- Mukherjee, D.; Moliterno, D.J. Effectiveness of PCI for non-acute coronary artery disease. Lancet 2009, 373, 870–872. [Google Scholar] [CrossRef]
- Tonino, P.A.L.; De Bruyne, B.; Pijls, N.H.J.; Siebert, U.; Ikeno, F.; van’t Veer, M.; Klauss, V.; Manoharan, G.; Engstrøm, T.; Oldroyd, K.G.; et al. Fractional flow reserve versus angiography for guiding percutaneous coronary intervention. N. Engl. J. Med. 2009, 360, 213–224. [Google Scholar] [CrossRef] [Green Version]
- De Bruyne, B.; Pijls, N.H.; Kalesan, B.; Barbato, E.; Tonino, P.A.; Piroth, Z.; Jagic, N.; Mobius-Winckler, S.; Rioufol, G.; Witt, N.; et al. Fractional flow reserve-guided PCI versus medical therapy in stable coronary disease. N. Engl. J. Med. 2012, 367, 991–1001. [Google Scholar] [CrossRef] [Green Version]
- Fearon, W.F.; Zimmermann, F.M.; De Bruyne, B.; Piroth, Z.; van Straten, A.H.; Szekely, L.; Davidavičius, G.; Kalinauskas, G.; Mansour, S.; Kharbanda, R.; et al. Fractional Flow Reserve-Guided PCI as Compared with Coronary Bypass Surgery. N. Engl. J. Med. 2022, 386, 128–137. [Google Scholar] [CrossRef]
- Pijls, N.H.; van Schaardenburgh, P.; Manoharan, G.; Boersma, E.; Bech, J.-W.; Veer, M.V.; Bär, F.; Hoorntje, J.; Koolen, J.; Wijns, W.; et al. Percutaneous coronary intervention of functionally nonsignificant stenosis: 5-year follow-up of the DEFER Study. J. Am. Coll. Cardiol. 2007, 49, 2105–2111. [Google Scholar] [CrossRef] [Green Version]
- Monlezun, D.J.; Hostetter, L.; Balan, P.; Palaskas, N.; Lopez-Mattei, J.; Cilingiroglu, M.; Iakobishvili, Z.; Ewer, M.; Marmagkiolis, K.; Iliescu, C. TAVR and cancer: Machine learning-augmented propensity score mortality and cost analysis in over 30 million patients. Cardiooncology 2021, 7, 25. [Google Scholar] [CrossRef]
- Monlezun, D.J.; Lawless, S.; Palaskas, N.; Peerbhai, S.; Charitakis, K.; Marmagkiolis, K.; Lopez-Mattei, J.; Mamas, M.; Iliescu, C. Machine Learning-Augmented Propensity Score Analysis of Percutaneous Coronary Intervention in Over 30 Million Cancer and Non-cancer Patients. Front. Cardiovasc. Med. 2021, 8, 620857. [Google Scholar] [CrossRef]
- Scullen, T.A.; Monlezun, D.J.; Siegler, J.E.; George, A.J.; Schwickrath, M.; El Khoury, R.; Cho, M.C.; Martin-Schild, S. Cryptogenic stroke: Clinical consideration of a heterogeneous ischemic subtype. J. Stroke Cerebrovasc. Dis. 2015, 24, 993–999. [Google Scholar] [CrossRef]
- Monlezun, D.J.; Samura, A.T.; Patel, R.S.; Thannoun, T.E.; Balan, P. Racial and Socioeconomic Disparities in Out-Of-Hospital Cardiac Arrest Outcomes: Artificial Intelligence-Augmented Propensity Score and Geospatial Cohort Analysis of 3952 Patients. Cardiol. Res. Pract. 2021, 2021, 3180987. [Google Scholar] [CrossRef] [PubMed]
- Garstka, M.E.; Monlezun, D.; DuCoin, C.; Killackey, M.; Kandil, E. The Sunshine Act and Surgeons: A Nation-Wide Analysis of Industry Payments to Physicians. J. Surg. Res. 2019, 233, 41–49. [Google Scholar] [CrossRef] [PubMed]
- D’Agostino, R.B., Jr. Propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group. Stat. Med. 1998, 17, 2265–2281. [Google Scholar] [CrossRef]
- Elze, M.C.; Gregson, J.; Baber, U.; Williamson, E.; Sartori, S.; Mehran, R.; Nichols, M.; Stone, G.W.; Pocock, S.J. Comparison of Propensity Score Methods and Covariate Adjustment: Evaluation in 4 Cardiovascular Studies. J. Am. Coll. Cardiol. 2017, 69, 345–357. [Google Scholar] [CrossRef]
- Kwok, C.S.; Wong, C.W.; Kontopantelis, E.; Barac, A.; Brown, S.-A.; Velagapudi, P.; A Hilliard, A.; Bharadwaj, A.S.; Alraies, M.C.; Mohamed, M.; et al. Percutaneous coronary intervention in patients with cancer and readmissions within 90 days for acute myocardial infarction and bleeding in the USA. Eur. Hear. J. 2021, 42, 1019–1034. [Google Scholar] [CrossRef] [PubMed]
- Balanescu, D.V.; Aziz, M.K.; Donisan, T.; Palaskas, N.; Lopez-Mattei, J.; Hassan, S.; Kim, P.; Song, J.; Ntim, W.; Cilingiroglu, M.; et al. Cancer treatment resumption in patients with new-generation drug-eluting stents. Coron. Artery Dis. 2021, 32, 295–301. [Google Scholar] [CrossRef]
- Das, D.; Asher, A.; Ghosh, A.K. Cancer and Coronary Artery Disease: Common Associations, Diagnosis and Management Challenges. Curr. Treat. Options Oncol. 2019, 20, 46. [Google Scholar] [CrossRef]
- Whitlock, M.C.; Yeboah, J.; Burke, G.L.; Chen, H.; Klepin, H.D.; Hundley, W.G. Cancer and Its Association With the Development of Coronary Artery Calcification: An Assessment From the Multi-Ethnic Study of Atherosclerosis. J. Am. Hear. Assoc. 2015, 4, e002533. [Google Scholar] [CrossRef] [Green Version]
- Koene, R.J.; Prizment, A.E.; Blaes, A.; Konety, S.H. Shared Risk Factors in Cardiovascular Disease and Cancer. Circulation 2016, 133, 1104–1114. [Google Scholar] [CrossRef] [Green Version]
- Reicher-Reiss, H.; Jonas, M.; Goldbourt, U.; Boyko, V.; Modan, B. Selectively increased risk of cancer in men with coronary heart disease. Am. J. Cardiol. 2001, 87, 459–462. [Google Scholar] [CrossRef]
- Landes, U.; Kornowski, R.; Bental, T.; Assali, A.; Vaknin-Assa, H.; Lev, E.; Iakobishvili, Z. Long-term outcomes after percutaneous coronary interventions in cancer survivors. Coron. Artery Dis. 2017, 28, 5–10. [Google Scholar] [CrossRef] [PubMed]
- Kanenawa, K.; Yamaji, K.; Morinaga, T.; Hiromasa, T.; Hayashi, M.; Hiramori, S.; Tomoi, Y.; Kuramitsu, S.; Domei, T.; Hyodo, M.; et al. Clinical Outcomes After Percutaneous Coronary Intervention in Patients With Cancer. Circ. J. 2021, 85, 837–846. [Google Scholar] [CrossRef] [PubMed]
- Kupeli, S. Risks and diagnosis of coronary artery disease in Hodgkin lymphoma survivors. World J. Cardiol. 2014, 6, 555–561. [Google Scholar] [CrossRef] [PubMed]
- Lee, M.S.; Finch, W.; Mahmud, E. Cardiovascular complications of radiotherapy. Am. J. Cardiol. 2013, 112, 1688–1696. [Google Scholar] [CrossRef] [PubMed]
- Ng, A.K. Review of the cardiac long-term effects of therapy for Hodgkin lymphoma. Br. J. Haematol. 2011, 154, 23–31. [Google Scholar] [CrossRef] [PubMed]
- Zamorano, J.L.; Lancellotti, P.; Rodriguez Munoz, D.; Aboyans, V.; Asteggiano, R.; Galderisi, M.; Habib, G.; Lenihan, D.J.; Lip, G.Y.; Lyon, A.R.; et al. 2016 ESC Position Paper on cancer treatments and cardiovascular toxicity developed under the auspices of the ESC Committee for Practice Guidelines: The Task Force for cancer treatments and cardiovascular toxicity of the European Society of Cardiology (ESC). Eur. Heart J. 2016, 37, 2768–2801. [Google Scholar] [CrossRef]
- Yuan, C.; Parekh, H.; Allegra, C.; George, T.J.; Starr, J.S. 5-FU induced cardiotoxicity: Case series and review of the literature. Cardiooncology 2019, 5, 13. [Google Scholar] [CrossRef] [Green Version]
Variable, (%) | Sample | PCI Alive (97.22%) | p-Value | |
---|---|---|---|---|
Without FFR (96.91%) | With FFR (3.39%) | |||
Demographic | ||||
Age, mean (SD) | 64.80 (12.99) | 64.77 (13.04) | 65.50 (11.63) | <0.001 |
Female | 38.24 | 38.25 | 37.81 | 0.429 |
Non-white race | 27.75 | 27.85 | 24.58 | <0.001 |
Insurance | 0.004 | |||
Commercial | 26.87 | 26.90 | 26.20 | |
Medicare | 55.37 | 55.30 | 57.35 | |
Medicaid | 10.64 | 10.66 | 9.94 | |
Veterans Affairs | 2.87 | 2.88 | 2.73 | |
None | 4.25 | 4.26 | 3.78 | |
Income quartile | 0.006 | |||
1st (lowest) | 31.17 | 31.22 | 29.66 | |
2nd | 26.60 | 26.60 | 26.64 | |
3rd | 23.62 | 23.57 | 25.02 | |
4th (highest) | 18.61 | 18.61 | 18.69 | |
Comorbidities | ||||
Diabetes | 29.17 | 29.11 | 30.97 | <0.001 |
Hypertension | 80.83 | 80.66 | 85.82 | <0.001 |
Peripheral vascular disease | 7.83 | 7.68 | 7.83 | 0.623 |
Hyperlipidemia | 67.09 | 66.89 | 72.91 | <0.001 |
Smoking | 2.06 | 2.07 | 1.79 | 0.081 |
Obesity | 20.37 | 20.33 | 21.44 | 0.017 |
Poor diet | 0.30 | 0.30 | 0.24 | 0.363 |
Stroke | 4.46 | 4.46 | 4.52 | 0.785 |
Heart failure | 31.19 | 31.31 | 27.78 | <0.001 |
Cardiac arrest | 4.22 | 4.28 | 2.55 | <0.001 |
Valvular disease | 17.48 | 17.56 | 15.42 | <0.001 |
Smoking | 2.06 | 2.07 | 1.79 | 0.081 |
HIV | 0.19 | 0.19 | 0.14 | 0.285 |
Alcoholism | 3.95 | 3.96 | 3.51 | 0.045 |
Opiate dependence | 0.81 | 0.81 | 0.79 | 0.851 |
Anemia | 17.95 | 18.01 | 16.37 | <0.001 |
COPD | 19.38 | 19.35 | 20.15 | 0.078 |
Coagulopathy | 7.41 | 7.46 | 5.98 | <0.001 |
Depression | 9.34 | 9.31 | 10.01 | 0.037 |
Cirrhosis | 1.10 | 1.10 | 0.89 | 0.080 |
Chronic kidney disease (3–5) | 16.29 | 16.33 | 15.34 | 0.020 |
Acute myocardial infarction | 48.31 | 48.65 | 38.49 | <0.001 |
STEMI | 15.05 | 15.37 | 5.98 | <0.001 |
NSTEMI/UA | 33.53 | 33.56 | 32.75 | 0.135 |
Cardiogenic shock | 4.95 | 5.06 | 1.98 | <0.001 |
Cancer | 11.06 | 11.06 | 11.14 | 0.822 |
Active | 2.64 | 2.66 | 2.13 | 0.005 |
Metastasis | 0.72 | 0.73 | 0.29 | <0.001 |
Inpatient | ||||
Mortality risk, mean (SD) | 0.72 (0.99) | 0.72 (0.99) | 0.64 (0.92) | <0.001 |
Mortality | 2.78 | 2.84 | 1.10 | <0.001 |
LOS, mean (SD) | 5.48 (7.16) | 5.51 (7.21) | 4.70 (5.49) | <0.001 |
Cost USD, mean (SD) | 108,347.90 (133,058.10) | 108,533.10 (134,056.10) | 103,054.30 (100,274.10) | <0.001 |
Complications | 5.14 | 5.18 | 4.06 | <0.001 |
Bleed | 0.94 | 0.94 | 0.80 | 0.218 |
Stroke | 0.14 | 0.14 | 0.08 | 0.125 |
Acute kidney injury | 0.11 | 0.11 | 0.11 | 0.947 |
Variable | OR (95.0% CI) | p-Value |
---|---|---|
Age | 1.09, 1.09–1.10 | <0.001 |
Female | 1.07, 0.98–1.17 | 0.129 |
Race, nonwhite | 1.02, 0.95–1.09 | 0.652 |
Income quartile | ||
1st (lowest) | Reference | |
2nd | 1.32, 1.23–1.42 | <0.001 |
3rd | 1.52, 1.40–1.65 | <0.001 |
4th (highest) | 2.04, 1.86–2.23 | <0.001 |
Region | ||
New England | Reference | |
Mid Atlantic | 1.32, 1.13–1.56 | 0.001 |
East North Central | 1.61, 1.37–1.88 | <0.001 |
West North Central | 1.82, 1.52–2.18 | <0.001 |
South Atlantic | 1.84, 1.57–2.15 | <0.001 |
East South Central | 1.80, 1.51–2.15 | <0.001 |
West South Central | 2.48, 2.11–2.92 | <0.001 |
Mountain | 1.74, 1.44–2.09 | <0.001 |
Pacific | 2.26, 1.92–2.66 | <0.001 |
Urban density | ||
>=1 million central | Reference | |
>=1 million fringe | 0.91, 0.84–0.99 | 0.025 |
250,000–999,999 | 1.03, 0.95–1.11 | 0.509 |
50,000–249,999 | 1.03, 0.92–1.14 | 0.639 |
Micro | 1.03, 0.92–1.14 | 0.633 |
<Micro | 0.92, 0.82–1.40 | 0.189 |
Acute coronary syndrome | 1.26, 1.19–1.34 | <0.001 |
FFR | 0.47, 0.37–0.61 | <0.001 |
Cancer | ||
Cancer | 0.90, 0.82–0.98 | 0.013 |
With FFR | 1.20, 0.63–2.29 | 0.580 |
Metastasis | 1.91, 1.56–2.33 | <0.001 |
Mortality risk | 1.04, 1.01–1.07 | 0.011 |
Cancer | OR (95.0%CI) | p-Value |
---|---|---|
Overall | 1.15, 0.58–2.30 | 0.686 |
Primary malignancy | ||
Prostate | 1.80, 0.59–5.55 | 0.304 |
Skin | 1.16, 0.23–5.78 | 0.858 |
Breast | 0.67, 0.08–5.86 | 0.720 |
Lung | 1.27, 0.27–6.09 | 0.764 |
Bladder | 1.28, 0.14–11.39 | 0.822 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Chauhan, S.; Monlezun, D.J.; Kim, J.w.; Goel, H.; Hanna, A.; Hoang, K.; Palaskas, N.; Lopez-Mattei, J.; Hassan, S.; Kim, P.; et al. Fractional Flow Reserve Cardio-Oncology Effects on Inpatient Mortality, Length of Stay, and Cost Based on Malignancy Type: Machine Learning Supported Nationally Representative Case-Control Study of 30 Million Hospitalizations. Medicina 2022, 58, 859. https://doi.org/10.3390/medicina58070859
Chauhan S, Monlezun DJ, Kim Jw, Goel H, Hanna A, Hoang K, Palaskas N, Lopez-Mattei J, Hassan S, Kim P, et al. Fractional Flow Reserve Cardio-Oncology Effects on Inpatient Mortality, Length of Stay, and Cost Based on Malignancy Type: Machine Learning Supported Nationally Representative Case-Control Study of 30 Million Hospitalizations. Medicina. 2022; 58(7):859. https://doi.org/10.3390/medicina58070859
Chicago/Turabian StyleChauhan, Siddharth, Dominique J. Monlezun, Jin wan Kim, Harsh Goel, Alex Hanna, Kenneth Hoang, Nicolas Palaskas, Juan Lopez-Mattei, Saamir Hassan, Peter Kim, and et al. 2022. "Fractional Flow Reserve Cardio-Oncology Effects on Inpatient Mortality, Length of Stay, and Cost Based on Malignancy Type: Machine Learning Supported Nationally Representative Case-Control Study of 30 Million Hospitalizations" Medicina 58, no. 7: 859. https://doi.org/10.3390/medicina58070859