LETTERS FROM READERS
"Doctor, Should I Be Worried About This?"

“Doctor, ¿Me tengo que preocupar por esto?”

  • LUCIANO BATTIONI, 1  MTSAC  ORCID logo 
  • 1  Postgraduate Director in “Artificial Intelligence Applied to Health Sciences”. Universidad Nacional del Litoral. Santa Fe, Santa Fe

Rev Argent Cardiol 2025;93:161-162. https://doi.org/10.7775/rac.v93.i2.20877

Correspondence: Luciano Battioni, Calle 15 N.° 669, Mercedes, Buenos Aires. E-mail: lucianobattioni@gmail.com


2025 © Revista Argentina de Cardiología

Licencia Creative Commons  Creative Commons Atribution-NonCommercial-Sharelike 4.0 Internacional
This is an open-access article distributed under the terms of the Creative Commons Attribution License
 
 
 

If we could differentiate the universal goals of the medical sciences, we might conclude that there are three: diagnosis, prognosis, and treatment.

Their relative importance differs between patients and doctors. The question I have chosen to title this letter is probably the most important to the patient. However, it is the one that has received the least scientific and technical development.

In daily practice we use prognostic tools consistently and even dogmatically. In fact, many times we try to use scores generated to predict an event X in one population and extrapolate them to an event Y in another. (1) Most of these tools have areas under the ROC curve ranging from 0.60 to 0.85. (2,3) If we offered someone these tools to detect fraudulent banking transactions, they would quickly shake our hand and show us the way out.

This poor current predictive performance is due not only to multiple limitations and difficulties associated with healthcare data management, but also to the tools that have been used so far. In the work entitled Events Prediction Ability in Patients with Hypertension using Artificial Neural Network Analysis of Ambulatory Blood Pressure Monitoring Compared to Clinical Risk Stratification, Di Gennaro et al. developed a simple neural network model capable of predicting what will happen to our patients more accurately. (4)

Beyond the limitations acknowledged by the authors, it is worth highlighting what this work represents: the introduction of Artificial Intelligence (AI) tools into clinical practice. The integration of AI into medicine will change our practice in ways we cannot yet imagine. By integrating multiple variables, creating ones that we did not know existed or linking facts that elude human analysis, we will be able to provide precision medicine. (5)

But not all that glitters is gold. For example, neural networks tend to overfit, i.e. they have high internal validity, but when validated in external cohorts their performance can drop significantly.

To conclude, this work represents one of the first instances of using AI tools in medicine at a national level and, despite its design limitations, it gives us a very small sample of what this integration could represent and encourages us to continue research in this area.

 

Ethical considerations

Not applicable.

Conflicts of interest

None declared. (See authors' conflict of interests forms on the web).

 

REFERENCES

1. Wu JT, Wang SL, Chu YJ, Long DY, Dong JZ, Fan XW, et al. CHADS2 and CHA2DS2-VASc Scores Predict the Risk of Ischemic Stroke Outcome in Patients with Interatrial Block without Atrial Fibrillation. J Atheroscler Thromb 2017;24:176-84. https://doi.org/10.5551/jat.34900.
2. D'Agostino RB Sr, Vasan RS, Pencina MJ, Wolf PA, Cobain M, Massaro JM, et al. General cardiovascular risk profile for use in primary care: the Framingham Heart Study. Circulation 2008;117:743-53. https://doi.org/10.1161/CIRCULATIONAHA.107.699579
3. Olesen JB, Lip GY, Hansen ML, Hansen PR, Tolstrup JS, Lindhardsen J, et al. Validation of risk stratification schemes for predicting stroke and thromboembolism in patients with atrial fibrillation: nationwide cohort study. BMJ 2011; 342:d124. https://doi.org/10.1136/bmj.d124.
4. Di Gennaro F P, Catalano MP, Aguirre AG, Fernández ML, Llanos R, Pérez Lloretet S, et al. Events Prediction Ability in Patients with Hypertension using Artificial Neural Network Analysis of Ambulatory Blood Pressure Monitoring Compared to Clinical Risk Stratification. Rev Argent Cardiol 2025;93:33-42. https://doi.org/10.7775/rac.v93.i1.20854.
5. Topol E. Deep medicine: How artificial intelligence can make healthcare human again. Basic Books, 2019.

AUTHORS’ REPLY

We would like to thank Dr. Luciano Battioni for his accurate and enriching comments on our work entitled Events Prediction Ability in Patients with Hypertension using Artificial Neural Network Analysis of Ambulatory Blood Pressure Monitoring Compared to Clinical Risk Stratification. We agree that, while classical risk stratification models are used in the development of risk stratification models, the incorporation of new methodological tools, such as the analysis using artificial neural networks represents an opportunity that would allow us to optimize the diagnostic and prognostic accuracy of different variables, such as those

described in this study. These technologies make it possible to simultaneously integrate a large amount of data, identify patterns and generate more accurate predictions compared

to the methodological analysis tools that we usually use.

We recognize, as Dr. Battioni points out, that these models are not exempt from limitations, such as the risk of overfitting and the need for external validation. However, we believe that their development and implementation, carefully evaluated, can complement our clinical analysis and act as a valuable supportive tool to make more accurate decisions.

We hope that this work will contribute to the promotion of dialogue and interdisciplinary research between clinical medicine and data science, and we thank you once again for the careful reading and the valuable contributions you have made in your letter.

Yours sincerely,

Federico Di Gennaro
LETTERS FROM READERS
Target Organ Damage in Special Situations: Are we Measuring Correctly?

Daño de órgano blanco en situaciones especiales. ¿Estamos midiendo bien?

Rev Argent Cardiol 2025;93:162-163. https://doi.org/10.7775/rac.v93.i2.20886

Correspondence: Bruno Guarino. Av Córdoba 2351 7th Floor. CABA- Argentina E-mail: brunoguarino.med@gmail.com


Licencia Creative Commons  Creative Commons Atribution-NonCommercial-Sharelike 4.0 Internacional
This is an open-access article distributed under the terms of the Creative Commons Attribution License
 
 

I have read with interest the study by Travetto et al. "Detection of subclinical cardiac damage by echocardiography in a population of hypertensive patients with a high prevalence of obesity: discrepancies observed according to the indexing method used". (1) This is a descriptive, observational and prospective study that included 150 adult patients with arterial hypertension (AHT), where differences and concordances were compared when using echocardiographic measurements indexed by body surface area (ISC) vs. allometric indexes based on height (IAH). It represents, in my opinion, a bold attempt to take full advantage of the resources available in any echocardiography laboratory for a more accurate interpretation of the prevalence of target organ damage (WOD) in populations considered to be at high cardiovascular risk, such as patients with obesity, HT with left ventricular hypertrophy (LVH) or left atrial enlargement (LAA).

Since the 1980s, attempts have been made to index echocardiographic values for patients mainly with increased left ventricular mass or left atrial dilatation as a manifestation of increased pressure in the left circuit. (2) The difficulty of adequately assessing obese patients with hypertension seems to be overcome with use of AHI rather than ICS. In turn, it is difficult to interpret with the usual echocardiographic measurements to assess LAA when the body mass index (BMI) is greater than 35 kg/m². Therefore, early diagnosis using AHI is of high clinical value, highlighting the limitation of the most commonly used method in the echocardiography laboratories, such as measurement by ISC for this population (3)

An example of the usefulness of this work is the AAI reclassification rate in the overall population (28.5%) compared to the reclassification specifically in the population with a BMI greater than 40 kg/m² (55.4%). Considering that overweight was observed in 61.6% in the last survey on cardiovascular risk factors, the correct measurement of OBD in patients with obesity will undoubtedly represent a challenge in the coming years. (4) The greatest discrepancy between methods seems to be the IAA measured by HAI mainly in patients with AHT with body surface area greater than 35 kg/m².

Although the clinical practice and cardiovascular prevention guidelines of different scientific societies include assessment by AHI as a validated method, it is actually underused in daily practice in cardiac imaging services, which could reclassify patients with more extreme values by CSI, either by replacing this method or associating it with echocardiographic assessment for LVH and LAA in patients with grade I-II obesity or higher, mainly associated with a history of HT.

The incorporation of automatic indexing for AHI in echocardiography equipment, as well as its systematic use mainly in patients with AHT and BMI greater than 35/40 kg/m² could be very useful for early diagnosis and intensification of OBD treatment in this type of special population.

 

Ethical considerations

Not applicable

Conflicts of interest

The authors declare that they have no conflict of interest. (See conflict of interest form on the web).

 

REFERENCES

1. Travetto CM, Argento LV. Detection of subclinical cardiac damage by echocardiography in a hypertensive population with high prevalence of obesity: discrepancies observed according to the indexing method used. Rev Argent Cardiol 2025;93:6-14. https://doi.org/10.7775/rac.es.v93.i1.20852.
2. de Simone G, Daniels SR, Devereux RB, Meyer RA, Roman MJ, de Divitiis O, et al. Left ventricular mass and body size in normo-tensive children and adults: assessment of allometric relations and impact of overweight. J Am Coll Cardiol 1992;20:1251-60. https://doi.org/10.1016/0735-1097(92)90385-z.
3. Stritzke J, Markus MR, Duderstadt S, Lieb W, Luchner A, Döring A, Keil U, et al; MONICA/KORA Investigators. The aging process of the heart: obesity is the main risk factor for left atrial enlargement during aging the MONICA/KORA (monitoring of trends and determinations in cardiovascular disease/cooperative research in the region of Augsburg) study. J Am Coll Cardiol 2009;54:1982-9. https://doi.org/10.1016/j.jacc.2009.07.034
4. National Institute of Statistics and Census - I.N.D.E.C. 4th National Survey of Risk Factors. Final results. - 1st ed. 2019. Autonomous City of Buenos Aires: INDEC.

 
 

AUTHORS’ REPLY

We thank Dr. Bruno Guarino for his interest in our work and agree with his words. The identification of valid indexes for the standardization of echocar diographic parameters related to body size in subjects with obesity is a complex issue. Many of these parame ters vary according not only to height, weight, muscle mass, total body fat mass but also to body fat distribu tion, and the coexistence of other metabolic disorders associated with obesity. (1)

For those parameters with methods and cut-off values defined in clinical practice guidelines for the obese population, we consider it important to rein force the need to incorporate them into routine prac tice. For those for which there is no consensus, it is crucial to always bear in mind the limitations of body surface area as an indexing method, especially in sub jects with severe or morbid obesity.

Conversely, in the context of medical practice, it is crucial for healthcare professionals to acknowledge that "clinical obesity," characterized by alterations in tissue or organ function due to excess adiposity, (2) is not merely a cardiovascular risk factor but rather a distinct disease entity, adversely impacting health and well-being. Therefore, a specific and multidisci plinary approach is necessary to prevent the develop ment of its complications, among which cardiovascu lar, metabolic, and renal diseases stand out. (2,3,4) It is imperative to acknowledge clinical obesity as a salient problem within the office setting so that people suffer ing from this condition can understand their risks and initiate treatment that will help them improve their quality of life and outcome.

Carolina Travetto
 

REFERENCES

1. Chantler PD, Lakatta EG. Role of body size on cardiovascular func tion: can we see the meat through the fat? Hypertension 2009;54:459- 61. https://doi.org/10.1161/HYPERTENSIONAHA.109.1344
2. Rubino F, Cummings DE, Eckel RH, Cohen RV, Wilding JPH, Brown WA, et al. Definition and diagnostic criteria of clinical obesity. Lancet Diabetes Endocrinol. 2025;13:221-62. https://doi.org/10.1016/ S2213-8587(24)00316-4.
3. Aguirre Ackermann M, Salinas MV, Torresani M, Cappelletti AM, Cafaro L, Menéndez E y col. Consenso intersocietario para el trata miento de la obesidad en adultos en Argentina. Revista de la Socie dad Argentina de Diabetes. 2023;57:3-47. https://doi.org/10.47196/ diab.v57i3.718
4. Arrupe M, Lavenia G (coord). Hipertensión Arterial en pacientes con Enfermedad Cardio-reno-metabólica: diagnóstico y tratamiento desde una mirada integral. Grupo de Trabajo de Cardiorrenometab olismo e HTA de la Sociedad Argentina de Hipertensión Arterial. 1a edición. Ciudad Autónoma de Buenos Aires: Sociedad Argentina de Hipertensión Arterial. 2024

 
 
LETTERS FROM READERS
Correlation of Ergospirometry with Echocardiography in Pulmonary Arterial Hypertension

Correlación de ergoespirometría con ecocardiograma en hipertensión arterial pulmonar

Rev Argent Cardiol 2025;93:164-165. https://doi.org/10.7775/rac.v93.i2.20887

Correspondence: Guillermina Sorasio. Las Heras 2670. Ciudad de Buenos Aires Correo electrónico: guillerminasorasio@gmail.com


Licencia Creative Commons  Creative Commons Atribution-NonCommercial-Sharelike 4.0 Internacional
This is an open-access article distributed under the terms of the Creative Commons Attribution License
 

Pulmonary arterial hypertension (PAH) is a heterogeneous, chronic and progressive entity that leads to remodeling of the pulmonary arterioles with subsequent increase in pulmonary vascular resistance (PVR) and right ventricular function impairment, the main predictor of mortality (1).

It is essential to perform adequate baseline risk and follow-up stratification in these patients in order to initiate early treatment based on known risk scores. (2)

Although the 6-minute walk test is the most accessible and simple technique to assess functional capacity, it has certain limitations such as the influence of sex, age, height, weight, comorbidities and learning curve, among others. For this reason, ergospirometry or cardiopulmonary exercise test (CPET) is the ideal method to determine exercise limitation, though it is not very accessible and expensive. (3)

As mentioned above, stratifying patients with PAH at baseline and during follow-up is a priority, and CPET with variables such as peak oxygen consumption (peak VO2 ) and ventilation to carbon dioxide production ratio (VE/VCO2) is an important part of it. (4)

Among the echocardiographic variables, the relationship between the tricuspid annular plane systolic excursion distance (TAPSE) and pulmonary artery systolic pressure (PASP) as a surrogate of ventricular arterial coupling, and the reduction of the stroke volume index (SVI) have been associated with poor prognosis in PAH.

The prognostic association between CPET variables, mainly VE/VCO2 ratio and VO2, and echocardiographic variables, as the TAPSE/PSAP ratio, is not well established.

The study by D' Amelio et al. evaluated the predictive ability of echocardiographic right ventricular function parameters in relation to exercise capacity, and compared CPET with the echocardiogram. Seven patients were included, most of them with PAH and chronic thromboembolic pulmonary hypertension (CTEPH). A statistically significant correlation was observed in the linear regression between TAPSE/PSAP ratio and peak VO2. Although the number of patients is limited for decision making, it is an interesting hypothesis when it comes to correlating the more accessible echocardiogram with CPET, thus allowing the assessment of the functional capacity of patients with PAH, which is an important prognostic parameter. The rest of the CPET variables such as the VE/VCO2 slope and Doppler echocardiogram variables, as fractional area and right atrial diameter change did not show statistical association. (5)

This is a very interesting study that when applied to a larger number of patients will allow us to evaluate other significant associations of echocardiographic variables with CPET and enable their application to daily clinical practice.

 

Ethical considerations

Not applicable

Conflicts of interest

None declared. (See authors conflicts of interest forms on the website).

 

REFERENCES

1. Humbert M, Kovacs G, Hoeper MM, Badagliacca R, Berger RM, Brida M, et al; ESC/ERS Scientific Document Group. 2022 ESC/ ERS Guidelines for the diagnosis and treatment of pulmonary hypertension. Eur Heart J 2022;3:3618-731. https://doi.org/10.1093/ eurheartj/ehac237
2. Benza RL, Kanwar MK, Raina A, Scott JV, Zhao CL, Selej M, Elliott CG, Farber HW. Development and Validation of an Abridged Version of the REVEAL 2.0 Risk Score Calculator, REVEAL Lite 2, for Use in Patients With Pulmonary Arterial Hypertension. Chest 2021;159:337-46. https://doi.org/10.1016/j.chest.2020.08.2069
3. Sherman AE, Saggar R. Cardiopulmonary Exercise Testing in Pulmonary Arterial Hypertension. Heart Fail Clin 2023;19:35-43. https://doi.org/10.1016/j.hfc.2022.08.015.
4. Dmytriiev K, Stickland M, Weatherald J. Cardiopulmonary Exercise Testing in Pulmonary Hypertension Heart Fail Clin 2025;21:51-61. https://doi.org/10.1016/j.hfc.2024.05.002.
5. D’ Amelio N, Kaplan P, Lago M, Souto G, Amor M, Bruzzese M. Ergospirometry in Patients with Precapillary Pulmonary Hypertension: Evaluation of the Predictive Value of Echocardiographic Variables. Rev Argent Cardiol 2025; 93:83-5. https://doi.org/10.7775/rac.es.v93.i1.20853.

 

AUTHORS’ REPLY

I would like to thank Dr. Sorasio for her detailed and clear summary of the role played by each variable analyzed in the risk stratification of patients with PH. In response, I would like to highlight as a strength of the study that we found the correlation between TAPSE/ sPAP and peak VO2 in chronic patients treated according to the risk established for each one, and without modifying the therapeutic the last two months. So, the possibility of using an echocardiogram variable as a surrogate for CPET could have application in the risk stratification of those patients in follow-up.

Nicolás D´Amelio
 
 

HTML generado desde un xml-jats a través de la plantilla jats-rac.xsl  por  RevisCiencia.  El motor utilizado es Apache Software Foundation (Xalan XSLTC).