¿Qué son los datos clínicos anonimizados?

Los datos clínicos anonimizados son información sobre la salud de los pacientes de la que se han eliminado los identificadores directos para proteger la privacidad. En el ámbito de la investigación, permiten a las organizaciones analizar tratamientos, resultados y patrones de enfermedades sin revelar información que permita identificar personalmente a los pacientes.

¿Cómo se recopilan los datos del mundo real a partir de los sistemas de historias clínicas electrónicas?

Los datos del mundo real procedentes de los sistemas de historias clínicas electrónicas (HCE) se recopilan durante la atención rutinaria al paciente y se registran en campos clínicos como el diagnóstico, la localización corporal, la gravedad de la enfermedad, el historial de tratamiento y los indicadores de resultados. Los datos estructurados y anonimizados de las HCE resultan especialmente útiles, ya que son más coherentes y están listos para su análisis.

¿Qué son los datos estructurados de las historias clínicas electrónicas y por qué son importantes para la investigación?

Los datos estructurados de la historia clínica electrónica (HCE) son información registrada en campos estandarizados, introducida directamente a partir de las respuestas del especialista a una serie de preguntas, en lugar de texto narrativo no estructurado. Son importantes para la investigación porque mejoran la coherencia del contenido de los datos introducidos por el especialista, facilitan un análisis más rápido y permiten evaluar más fácilmente los resultados de los pacientes, los patrones de tratamiento y la evolución de la enfermedad a gran escala.

¿Cómo pueden los datos de pacientes anonimizados y tokenizados contribuir a los estudios basados en evidencia del mundo real?

Los datos de pacientes anonimizados y tokenizados pueden servir de base para estudios de evidencia del mundo real, ya que permiten a los investigadores analizar los resultados al tiempo que contribuyen a proteger la privacidad. La tokenización también puede facilitar la vinculación a nivel de paciente entre conjuntos de datos dispares para garantizar el cumplimiento de la HIPAA, lo que permite obtener una visión más amplia de la trayectoria de los pacientes, el uso de los tratamientos y los resultados a largo plazo.

¿Qué tipos de indicadores de resultados pueden incluir los datos del mundo real específicos de cada especialidad?

Los datos del mundo real específicos de cada especialidad pueden incluir medidas de resultado como las puntuaciones de gravedad de la enfermedad, la localización corporal, la agudeza visual, la presión intraocular, las características de las lesiones, los índices de síntomas y la evolución a lo largo del tiempo. Estas medidas estructuradas ayudan a los investigadores a evaluar la carga de la enfermedad, la respuesta al tratamiento y los resultados clínicos.

¿Por qué utilizan los equipos del ámbito de las ciencias de la vida conjuntos de datos clínicos específicos de cada especialidad?

Los equipos del ámbito de las ciencias de la vida utilizan conjuntos de datos clínicos específicos de cada especialidad, ya que estos proporcionan un contexto clínico más detallado que muchas fuentes generalizadas. Estos conjuntos de datos pueden ofrecer indicadores relevantes para la enfermedad, información sobre los tratamientos y detalles sobre los resultados que mejoran el diseño de los estudios, la generación de evidencia y el análisis de las áreas terapéuticas.

¿Cuál es la diferencia entre los datos del mundo real y la evidencia del mundo real?

Los datos del mundo real son la información sanitaria recopilada durante la atención sanitaria habitual, procedente de historias clínicas electrónicas, reclamaciones o datos sobre resultados. La evidencia del mundo real es el conocimiento clínico o científico que se obtiene al analizar los datos del mundo real para responder a preguntas sobre el uso de los tratamientos, su seguridad, su eficacia o los resultados de los pacientes. La envergadura y el nivel de detalle de las soluciones de datos del mundo real de ModMed contribuyen a generar evidencia del mundo real más precisa para los investigadores del ámbito de las ciencias de la vida.

¿Qué deben tener en cuenta los investigadores a la hora de elegir un proveedor de datos del mundo real?

Los investigadores deben tener en cuenta la calidad de los datos, la estructura de los campos, la pertinencia para su especialidad, las medidas de protección de la privacidad, las capacidades de tokenización, la amplitud geográfica y la profundidad de los resultados. Un buen proveedor de datos del mundo real también debe ofrecer conjuntos de datos listos para su análisis que se ajusten a la pregunta de investigación y al diseño del estudio previstos.

Schweiger Dermatology Group is the largest dermatology provider in the Northeast. Before we used Clara, we were primarily a telephone based company. We had a central call center, but there was a lot of delay in communications. One of the biggest challenges we face as a practice is the, we call it like the endless circle of phone tag with our patients where, you know, a patient calls in, we send in a request to our clinical team. They have to then call the patient back and they're leaving a voicemail. Patient then calls back and that loop continues again and again. Clara does a great job of trying to prevent phone tag. It makes it easy for the patient. The interface with Clara is very straightforward. It's nice that they don't need a password to log in, that it can be done right through their text messaging, which pretty much everybody's comfortable with now. There's not a lot of extra button pushing, not a lot of extra web pages to scroll to, no app to download. It's really very easy to use. Once we implemented Clara, we put the patient in direct contact with the provider, cutting out the middleman and the message taking, and patients were able to get answers right away. We've saved hundreds and hundreds of hours of phone calls. I think one of the ways that Clara differentiates themselves from other platforms is their transparency. The ability to see all of the conversation between a patient, everything internally and externally that's happening between a staff member and a patient really allows everybody to be in the know and take any action needed. They seek to understand our problem and they come to us with really creative solutions. They've been an amazing partner from the beginning. Using Clara has definitely improved our revenue because we've been able to increase our numbers of patients. It does give the patient a little bit more control, is something you don't generally see in antiquated medical communications. Clara really does show innovation. The way we use it has worked very well with our patient support center. I would absolutely recommend Clara to other healthcare providers. I think we would still be in the dark ages of communication if we didn't use Clara.

Structured real-world data to drive life science and outcomes research

Eliminate the delay between data and discovery

A medical software user interface displaying a human body outline with selectable points for logging symptoms. A right-hand panel titled 'Morphology' includes a search bar, a 'Total Body Surface Area' slider set to 20%, a 'Psoriasis PGA' field set to Severe, and an 'Itch Numeric Rating Scale' slider set to 8.

Clinical data without the cleanup

Breakthrough research shouldn’t stall because you have to spend months untangling free-text clinical notes before running a query. ModMed® Real-World Data (RWD) Solutions delivers de-identified, tokenized datasets ready for use. Because we capture every granular detail as structured data right in the exam room, there are no messy narratives to decipher.

Whether you are generating real-world evidence, conducting outcomes research, or running life sciences analyses, ModMed provides organized datasets so you can stop cleaning data and get straight to the insights.

The ModMed RWD Solutions data advantage

A simple black and white line icon depicting three stacked computer server racks connected by a network line, representing a database or structured data.

Structured and de-identified

Bypass messy, unstructured narratives with data that is primed for clinical and operational modeling. ModMed equips your researchers with anonymized, highly structured data captured directly at the point of care.

A simple black and white line icon showing a hierarchical tree diagram, with a single node on the left branching out into three separate nodes on the right, representing granularity or specialty-specific data.

Specialty-specific and granular

Power your most complex research with specialty-specific datasets captured at the granular level. With it, you get the variables needed to analyze rare and common disease populations, track outcomes, and measure real-world product use.

Longitudinal and tokenized

Build reliable real-world evidence by following patients across multiple visits. Tokenized longitudinal continuity allows researchers to see the complete context, measure true clinical progression, track operational decisions over time, and accurately assess long-term patient outcomes.

Robust nationwide specialty representation

ModMed maintains extensive data across the dermatology and ophthalmology specialties, with a growing network that continues to expand. Captured at a granular level in structured fields within our award-winning EHR¹ and delivered in an analysis-ready format, our data supports life sciences organizations working on real-world evidence (RWE), and health economics and outcomes research (HEOR), and more.

󿁘

Dermatology

󿁜

Ophthalmology

ModMed RWD Solutions provide extensive dermatology data², such as:

Disease	Estimated patient count	Key outcome measures
Psoriasis	4.5M	Location, PGA, BSA, Itch-NRS, PASI
Atopic Dermatitis	5.9M	Location, overall assessment, BSA, Itch Index, EASI
Hidradenitis Suppurativa	750K	Location, Hurley stage
Alopecia Areata	820K	Location, severity score
Melanoma	1.1M	Location, stage, lesion diameter

A stylized network map of the United States displaying healthcare statistics: 417 million plus total visits, 263 million plus total prescriptions, 98 million plus total patients, and 16 thousand total derm providers.

Dermatology

Extensive data from our network of:

98M+ patients
481M+ encounters

ModMed RWD Solutions provide extensive ophthalmology data², such as:

Disease	Estimated patient count	Key outcome measures
Dry Eye	5.8M	Schirmer’s test, tear breakup time, tear film osmolarity
Glaucoma	1.7M	Visual acuity, visual field test, IOP
Dry AMD	1.2M	Visual acuity, IOP
Wet AMD	340K	Visual acuity, IOP

A purple stylized network map of the United States displaying healthcare statistics: 102M+ total visits, 18M+ total patients, 25M+ total prescriptions, and 4K+ total Ophth providers.

Ophthalmology

Extensive data from our network of:

18M+ patients
102M+ encounters

Explore ModMed RWD Solutions

A female doctor in a white lab coat holds a tablet and smiles while having a conversation with a male patient in a brightly lit consultation room.

Get to know ModMed

#1 EHR

#1 dermatology EHR for 13 years in a row¹

#1 ophthalmology EHR for 10 years in a row¹

~1B

Patient encounters across 11 specialties

Technology Team of the Year

2025 Stevie American Business Awards (Silver)

FAQs

What is de-identified clinical data?

De-identified clinical data is patient health information that has had direct identifiers removed to help protect privacy. In research, it allows organizations to analyze treatments, outcomes, and disease patterns without exposing personally identifiable patient information.

How is real-world data collected from EHR systems?

Real-world data from EHR systems is collected during routine patient care and captured in clinical fields such as diagnosis, body location, disease severity, treatment history, and outcome measures. Structured, de-identified EHR data is especially useful because it is more consistent and ready for analysis.

What is structured EHR data, and why does it matter for research?

Structured EHR data is information recorded in standardized fields, directly input from questions the specialist answers, rather than unstructured narrative text. It matters for research because it improves consistency of the data content entered by the specialist, supports faster analysis, and makes it easier to evaluate patient outcomes, treatment patterns, and disease progression at scale.

How can de-identified, tokenized patient data support real-world evidence studies?

De-identified, tokenized patient data can support real-world evidence studies by enabling researchers to analyze outcomes while helping protect privacy. Tokenization can also facilitate patient-level linkage across disparate datasets to support HIPAA compliance, creating a broader view of patient journeys, treatment use, and longitudinal outcomes.

What types of outcome measures can specialty-specific real-world data include?

Specialty-specific real-world data can include outcome measures such as disease severity scores, body location, visual acuity, intraocular pressure, lesion characteristics, symptom indexes, and progression over time. These structured measures help researchers evaluate disease burden, treatment response, and clinical outcomes.

Why do life sciences teams use specialty-specific clinical datasets?

Life sciences teams use specialty-specific clinical datasets because they provide deeper clinical context than many generalized sources. These datasets can offer disease-relevant measures, treatment insights, and outcome details that improve study design, evidence generation, and therapeutic area analysis.

What is the difference between real-world data and real-world evidence?

Real-world data refers to health information collected during routine care, sourced from EHRs, claims, or outcomes data. Real-world evidence is the clinical or scientific insight generated by analyzing real-world data to answer questions about treatment use, safety, effectiveness, or patient outcomes.

The scale and granularity of ModMed Real-World Data Solutions help drive more accurate real-world evidence for life science researchers.

What should researchers look for in a real-world data provider?

Researchers should look for data quality, structured fields, specialty relevance, privacy protections, tokenization capabilities, geographic breadth, and outcomes depth. A strong real-world data provider should also deliver analysis-ready datasets that align with the intended research question and study design.

󿂁

Meet our ModMed RWD Solutions team

Start now

Tom Haskell

General Manager, Real-World Data
ModMed

Tim Baumann

Real-World Data Sales Executive
ModMed

Rick Catino

Vice President, Real-World Data
ModMed

1 2026 Black Book^™
2 Data reflected are sample estimates. Patient counts may vary depending on inclusion parameters and terms.

Welcome Back