Electronic – AD5933 takes much longer to perform a frequency sweep than expected

I've been trying to replicate a 2015 paper that uses electrical impedance tomography to map a cross-section of a hand. They use the AD5933 bio-impedance analyzer.

On page 3 of the paper, they say they could achieve a sample speed of 3ms per sample, but performing a simple, single frequency sweep with the same chip takes me over 90 ms on average.

I'm using modified code from a different project for the AD5933 and Arduino. I've included the parts I think are relevant (although I understand usually the code contained in a post isn't always the offending segment, I'm shortening it to not make the question too long).

//ALL CAPS VARIABLES ARE SET TO THE HEX VALUES SPECIFIED IN THE DATASHEET (AFTER PAGE 23)
//PROGRAMS THE REGISTERS BEFORE A SWEEP. TAKES AROUND 25ms, BUT ONLY NEEDS TO BE PERFORMED ONCE PER FRAME

void programReg() {

  // Set Range 1, PGA gain 1
  writeData(CTRL_REG,0x01);
  // Set settling cycles
  writeData(NUM_SCYCLES_R1, 0x07);
  writeData(NUM_SCYCLES_R2, 0xFF);

  // Start frequency of 1kHz
  writeData(START_FREQ_R1, getFrequency(start_freq,1));
  writeData(START_FREQ_R2, getFrequency(start_freq,2));
  writeData(START_FREQ_R3, getFrequency(start_freq,3));

  // Increment by 1 kHz
  writeData(FREG_INCRE_R1, getFrequency(incre_freq,1));
  writeData(FREG_INCRE_R2, getFrequency(incre_freq,2));
  writeData(FREG_INCRE_R3, getFrequency(incre_freq,3));

  // Points in frequency sweep (100), max 511
  writeData(NUM_INCRE_R1, (incre_num & 0x001F00)>>0x08 );
  writeData(NUM_INCRE_R2, (incre_num & 0x0000FF));
}

//CODE WHERE THE ACTUAL SWEEP IS PERFORMED
void runSweep() {
  Serial.print("0: ");
  Serial.println(micros()-t);
  short re;
  short img;
  double freq;
  double mag;
  double phase;
  double gain;
  double impedance;
  double tot=0;
  double avg;
  double a, b, c;
  int i = 0;
  int j = 0;
  int flag = 0;
  boolean w_f;

  programReg();

  // 1. Standby '10110000' Mask D8-10 of avoid tampering with gains
  writeData(CTRL_REG,(readData(CTRL_REG) & 0x07) | 0xB0);

  // 2. Initialize sweep
  writeData(CTRL_REG,(readData(CTRL_REG) & 0x07) | 0x10);

  // 3. Start sweep
  writeData(CTRL_REG,(readData(CTRL_REG) & 0x07) | 0x20);
  w_f = (readData(STATUS_REG) & 0x07) < 4 ; //Checks if the frequency sweep is not complete
  Serial.print("1: ");
  Serial.println(micros()-t);
  while (w_f) {
    flag = readData(STATUS_REG)& 2; //This is true if there is valid data in the register (DS, pg. 26)
    Serial.print("2: "); 
    Serial.println(micros()-t);
    while (flag != 2) {
      delay(3);
      flag = readData(STATUS_REG)& 2;
      Serial.print("2.1: ");
      Serial.println(micros()-t);
      if (flag == 2) {
        byte R1 = readData(RE_DATA_R1);
        byte R2 = readData(RE_DATA_R2);
        re = (R1 << 8) | R2;

        R1  = readData(IMG_DATA_R1);
        R2  = readData(IMG_DATA_R2);
        img = (R1 << 8) | R2;

        freq = start_freq + i*incre_freq;
        mag = sqrt(pow(double(re),2)+pow(double(img),2));
        Serial.print("3: ");
        Serial.println(micros()-t);

        Serial.print(" Resistance: ");
        Serial.print(re);
        Serial.print(",");

        Serial.print(" Reactance: ");
        Serial.print(img);

        // break;  //TODO: for single run, remove after debugging
      
        //Increment frequency
        w_f = (readData(STATUS_REG) & 0x07) < 4 ;
        if (w_f) {
          writeData(CTRL_REG,(readData(CTRL_REG) & 0x07) | 0x30);
        }
        Serial.print("4: ");
        Serial.println(micros()-t);
      }
    }
    // Power down
    // writeData(CTRL_REG,0xA0);
  }
  writeData(CTRL_REG,(readData(CTRL_REG) & 0x07) | 0xA0);
}

I have timing markers on the runSweep() function that return this (numbers in microseconds from micros()):

1: 25096.00
2: 27900.00
2.1: 33724.00
2.1: 39572.00
2.1: 45412.00
2.1: 51256.00
2.1: 57104.00
2.1: 62944.00
2.1: 68792.00
2.1: 74644.00
2.1: 80488.00
3: 90012.00
 Resistance: -106, Reactance: 301, Impedence: 37267.40
4: 97448.00
2: 100260.00
2.1: 106132.00
2.1: 112020.00
2.1: 117912.00
2.1: 123808.00
2.1: 129712.00
2.1: 135600.00
2.1: 141468.00
2.1: 147340.00
2.1: 153212.00
3: 162772.00
Resistance: -146, Reactance: 418, Impedence: 26873.24
4: 166912.00
Last: 170948.00

My question is: How do I decrease the time it takes for a sweep to be performed?

I've tried: setting the speed of the Wire.h library to 400000Hz (the fastest timing), and skipping the flag check step after a 5 ms delay (led to useless data). On the hardware side, I tried replacing the chip, to no avail. I've run out of ideas, so any help is greatly appreciated.

Edit: In another function which samples the entire frame of electrode pairs, I use the repeat frequency command, but this doesn't cause a noticeable speed boost.

Edit 2: I've added an answer as a community wiki. The problem was in programReg() specifically the Set settling cycles portion.