Medical Cards for Croydon Schoolchildren 1920s-1930s

Sample Medical Card for Croydon Schoolboys 1920s-1930s
Sample Medical Card for Croydon Schoolboys 1920s-1930s

Historians must make more – and more creative – use of AI technologies for data analysis as well as for routine task of data sorting and transcription. To create a simple example, I have put to work an otherwise stagnant set of 93 medical records collected in the 1920s and 1930s from school children in Croydon, UK. These records had been forgotten, consigned to a pile of uncatalogued miscellany in permanent storage. In this post, I explore the basic possibilities for activation and analysis using the GoogleNotebookLM.

These archival documents consist of a series of longitudinal health records for male students in the borough of Croydon during the late 1920s and 1930s. Each individual card tracks a child’s physical development over three distinct examinations, meticulously documenting changes in age, height, and weight alongside a history of infectious illnesses. By recording these biometric data points at different intervals, the source provides a detailed chronicle of growth and public health status within a specific educational cohort. The systematic nature of these entries suggests a formal institutional effort to monitor the well-being and maturation of schoolchildren over time.

Wellcome Collection holds reports from the Medical Officer of Health for Croydon as part of London’s Pulse: Medical Officer of Health reports 1848-1972.

These medical cards were in UCL Department of Statistical Science’s department library, no doubt, due to Karl Pearson. Pearson was forever in search of real numbers, i.e., data collected from the real world. He wanted data sets that reflected the world’s messy, noisy nature. For Pearson, these data sets provided grist for his statistical mills. He used these for his own research (both developing new statistical tools and using those tools on projects of interest to him), projects given to research students, and projects assigned to research associates in the Biometric Laboratory and the Eugenics Laboratory. Public health data was ideal for Pearson because it was widely available, and it was available in bulk. With his commitment to eugenics, he also was on the lookout for data to support ideological conclusions.

These medical cards seem to have been transcribed from another source, probably original medical records. (The handwriting and ink are consistent throughout, unlikely for original record-keeping over eleven years.) The data collection began in 1926 and ended in 1937. Pearson retired in 1933, but he remained mildly active as a researcher until his death in April 1936. The last recorded examination is 05 February 1937. I have yet to find evidence these cards were studied in the department. The data was used in standard public health reporting for borough health officers.

Medical Cards are Available as Open Data

On the principle of Open Data, the dataset is available for further GenAI analysis via my sharing account through GoogleNotebookLM. Further, the dataset as scanned pages is downloadable as one pdf (below), and a transcribed dataset is available as a spreadsheet (*.csv file in *.zip). The transcription generated within one minute. The production of a data table proved more challenging. When attempted in an hour of high server demand, the LM failing to complete the work. In a low demand hour, the response was speedy. The prompt included information on how to interpret various elements of the medical card as well as formatting requests for the output.

Prompt used to create the transcription and table creation

Medical Cards Analysed by GoogleNotebookLM

To assess the clarity and value of analysis by the LM, a series of prompts were submitted. Below are the prompts and responses received.

How many medical cards are present?

Are any numbers missing?

What is the distribution of infectious illnesses?

What is the distribution of boroughs? “Croydon” is one borough.

For the dates, the sequence is Day.Month.Year. What is the distribution of dates for examination 1, 2, and 3?

What is the average age of the children in each examination? The data is presented in the form “years.months”. report the results in the same form.

Calculate the standard deviation for these results. Keep the data in months.

Height is measured in inches. Weight is measured in pounds. Calculate the average and standard deviations for height and weight for year examination.

What is the correlation between number of infections and the increase in height and weight between examination 1 and 3?

Calculate the correlation coefficient for the number of infections and the increase in height and weight between examination 1 and 3.

Does height and weight correlate at Examination I?

To explore the state and value of products offered by GoogleNotebookLM, below are a series of outputs generated by that LM, including an audio description, an infographic, and a blogpost. The LM was given only the medical cards.

Audio Description created by GoogleNotebookLM (unedited)

The instruction was to create a “deep dive” audio description, and no further prompt was given. The only material provided to the generator was the pdf containing all medical cards (below). This audio description is unedited.

Infographic created by GoogleNotebookLM (notice biases)

Infographic of Medical Cards from Croydon Schoolchildren 1920s-1930s
Infographic of Medical Cards from Croydon Schoolchildren 1920s-1930s (created by GoogleNotebookLM)

Blogpost created by GoogleNotebookLM (unedited; notice errors/biases)

Growth, Grit, and Germs: What 100-Year-Old School Medical Cards Reveal about the Children of Croydon

History is often written in grand narratives of wars and treaties, but for the public health archivist, the most profound stories are found in the margins of administrative paperwork. A collection of 57 “Medical Cards for Schoolchildren” from the Borough of Croydon, spanning from 1926 to 1936, offers a meticulous window into the physical development of a generation. While modern parents are familiar with the routine of school physicals, these archival records reveal a highly systematic, three-stage longitudinal process—Stages I, II, and III—that tracked a child’s health with a level of analog precision that is both impressive and poignant.

A Childhood Defined by Infection

In the pre-antibiotic and pre-vaccine era of the late 1920s, infectious disease was not an outlier; it was a fundamental metric of childhood. The designers of these Croydon medical cards recognized this by placing a specific field at the very top of the card’s header, often filled in with the hurried, fluid script of a school medical officer:No. of infectious illnesses: NumberAcross this archive, these numbers tell a story of resilience—or “grit”—in the face of a persistent biological lottery. For instance, Child No. 20 and Child No. 57 both recorded five separate infectious illnesses during their school years. In contrast, children like No. 17 and No. 29 managed to record a “0,” representing a rare escape from the era’s common contagions. This tally was more than a statistic; it was a primary indicator of a child’s constitutional strength and the environmental pressures of interwar London.

Quarter-Inches and Fractional Pounds

Despite the lack of digital tools, the medical officers of the Borough of Croydon operated with striking meticulousness. The examination tables show that these health professionals were not merely rounding numbers; they were capturing the granular reality of growth.Measurements were recorded to the quarter-inch and fractional pound. For example, Child No. 15, examined on 16.9.27 at the age of 4.9, was recorded as precisely 38 1/2 inches tall and weighing 34 1/4 lbs. As an archivist, one notes the physical artifacts of this data entry: on Child No. 15’s second examination, there is a heavy ink smudge and correction over the weight of 46 1/2 lbs, suggesting a commitment to accuracy that required literal scratching out and rewriting. This level of detail was essential for identifying children falling behind developmental norms in a period of significant public health transition.

Tracking the Seven-Year Transformation

The true value of these cards lies in their longitudinal nature, capturing the biological “growing up” story of a child from age five through twelve or thirteen. These snapshots, taken years apart, document the profound physical transformation of puberty and childhood within the span of a single piece of cardstock.A dramatic growth sprint is visible in the record of Child No. 25. At his first examination (Stage I) at age 6.3, he stood 46 inches tall and weighed 53 lbs. By his final examination (Stage III) at age 13.0, he had grown to 64 inches and 113 lbs—an 18-inch height increase. Interestingly, when we contrast trajectories, we see the “grit” mentioned earlier: Child No. 20, despite his five infectious illnesses, grew 16 1/4 inches between ages 5.1 and 12.4. This nearly matches the 16 1/2-inch growth of the “zero-illness” Child No. 17, who was tracked over a slightly shorter period. It suggests that for many Croydon children, the pace of growth continued unabated by the frequent interruptions of disease.

The Bureaucracy of Well-Being

Beyond individual measurements, the collection demonstrates a high degree of administrative uniformity. Every card is headed “Borough of Croydon,” and the standardized format remains consistent across the decade. The use of the British date format (D.M.Y)—such as the “16.11.27” found on Child No. 20’s Stage I exam—and the consistent labeling of “Sex: M” across all 57 cards suggests these records likely represent a specific cohort from a gender-segregated Croydon Council School.The contrast between the rigid, typed headers and the varying flourishes of handwritten ink entries reflects an early 20th-century commitment to systematic oversight. This was a bureaucracy dedicated to the “well-being” of its future citizens, ensuring that every boy in the cohort was accounted for as he moved through the school system.

Lessons from the Archive

These medical cards are more than a collection of heights, weights, and illnesses; they are a testament to the lives of the children of Croydon. They remind us that today’s digital health footprints are simply the latest iteration of a century-old desire to measure, track, and protect the next generation.As we look at these handwritten fractions and ink-stained tallies, we must consider how our own health data will appear to historians a century from now. If your childhood were distilled into a single card of measurements and illnesses, what story would it tell?

Medical Cards (scanned from originals; downloadable)

The embedded pdf is the complete dataset of 93 medical records. It can be downloaded. It is open access data freely available.

Please credit: Professor Joe Cain and UCL Department of Statistical Science.

Provenance

These medical cards are in the public domain. The individuals are anonymous from the point of original data entry. It is not known which school these children attended or who made these measurements. The records came into my possession as part of a clearance project in UCL Department of Statistical Sciences. My working assumption is that these were sent to Karl Pearson but remained unanalysed. They were preserved as part of a large set of materials accumulated by Karl Pearson, then inherited as part of a department library until 2025 when the library was significantly reduced.

The original data cards remain in my possession.